© 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. 10-GEMMASCOPE-RES-131K
    7. 113274
    Prev
    Next
    INDEX
    Explanations

    implementation of software and algorithms

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

    the word "implemented" and its variants, particularly in technical or academic contexts describing system or algorithm implementations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on phrases describing how something was carried out or built—i.e. implementation language such as “implemented,” “implementation,” “using,” “by,” and “with.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     the
    -1.83
     realmente
    -1.83
     reliant
    -1.61
     probablemente
    -1.58
    に関して
    -1.55
     perché
    -1.55
     facilidad
    -1.53
    『
    -1.52
     generalmente
    -1.52
     пър
    -1.51
    POSITIVE LOGITS
    𓆜
    1.74
    衎
    1.73
    apa
    1.70
     Surprisingly
    1.66
    curité
    1.65
    with
    1.59
     Interestingly
    1.59
    ”，
    1.55
    Харак
    1.55
    ”。
    1.48
    Activations Density 0.069%

    No Known Activations