© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48227
    Prev
    Next
    INDEX
    Explanations

    programming code constructs

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

    The neuron fires on programming‐related identifiers and technical code tokens (e.g. class or enum names, exception types, function or module names).

    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
     only
    -2.50
     there
    -2.45
     even
    -2.38
     because
    -2.22
     if
    -2.17
    there
    -2.08
     Even
    -2.06
     There
    -1.98
     даже
    -1.94
     after
    -1.89
    POSITIVE LOGITS
    𓆏
    2.08
    chea
    1.90
     magnific
    1.81
    狲
    1.77
     lmao
    1.76
    ㋛
    1.76
    ^=
    1.73
     REALLY
    1.70
    rages
    1.63
     uska
    1.61
    Activations Density 0.010%

    No Known Activations