© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108959
    Prev
    Next
    INDEX
    Explanations

    web and app development file types

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron selectively activates on standalone numeric tokens (e.g. version numbers, IDs, or other digit sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical metadata and header sections in software files, especially configuration, versioning, licensing, and translation/localization headers.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    metadata or header information in technical documentation and source code files.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kval
    -1.00
     metode
    -0.82
    libat
    -0.81
    quial
    -0.79
    żeń
    -0.78
    脚注の使い方
    -0.77
     Metode
    -0.77
    corpus
    -0.76
     kommunik
    -0.75
     eki
    -0.75
    POSITIVE LOGITS
     URI
    0.94
     homeless
    0.81
     zweck
    0.78
    mText
    0.76
     태
    0.73
     ánimo
    0.71
     મા
    0.70
     homelessness
    0.70
    ZC
    0.68
    λαι
    0.68
    Activations Density 0.062%

    No Known Activations