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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103965
    Prev
    Next
    INDEX
    Explanations

    list headers or code elements

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

    words or tokens that are part of class names, package names, or technical identifiers in programming code.

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

    The neuron fires on CamelCase and other capitalized identifier tokens (e.g. Java class or type names and proper nouns).

    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
    '
    -2.58
     ilumina
    -2.41
     either
    -2.31
    );
    -2.19
     They
    -2.08
    enablog
    -1.99
     celé
    -1.93
     {
    -1.91
     my
    -1.87
     consider
    -1.81
    POSITIVE LOGITS
    鱨
    2.47
    檍
    2.47
     Août
    2.31
    ‪.‬‬
    2.30
    勠
    2.28
    ﱠ
    2.25
    CHREIB
    2.20
     brinquedo
    2.20
     Bedür
    2.20
    geſ
    2.19
    Activations Density 0.000%

    No Known Activations