© 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. 11947
    Prev
    Next
    INDEX
    Explanations

    code comments, especially ending blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    衚
    -1.97
    März
    -1.91
    鱨
    -1.83
    đại
    -1.79
    뿅
    -1.74
    戗
    -1.73
    놋
    -1.73
    텃
    -1.64
    ౭
    -1.63
    蠊
    -1.60
    POSITIVE LOGITS
     and
    2.09
     сделан
    1.78
     all
    1.76
    waf
    1.73
    .”
    1.68
     They
    1.60
     with
    1.58
    ”.
    1.55
     Since
    1.52
     each
    1.49
    Activations Density 0.001%

    No Known Activations