© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106818
    Prev
    Next
    INDEX
    Explanations

    licenses and copyrights

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

    The neuron fires on tokens written in all (or mostly) uppercase (often with underscores), such as macro names and license‐header keywords.

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

    legal and licensing boilerplate in source code headers and comments (e.g., copyright/author notices, license texts, and related metadata).

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

    copyright notices and legal/licensing headers in source code.

    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
    場合
    -0.73
     unbounded
    -0.71
    ライト
    -0.68
    Cách
    -0.68
     Kathleen
    -0.68
    今晚
    -0.67
    Kathleen
    -0.67
    要做
    -0.66
     obro
    -0.65
    SSN
    -0.65
    POSITIVE LOGITS
    '}>
    0.72
     profiles
    0.68
    Gost
    0.65
    べて
    0.65
     Mercier
    0.65
    imer
    0.64
    Profiles
    0.63
    rítica
    0.63
    SEL
    0.63
    kó
    0.63
    Activations Density 0.061%

    No Known Activations