© 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. 23865
    Prev
    Next
    INDEX
    Explanations

    introduces subsequent actions or states

    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
    皤
    -3.31
    樒
    -3.11
    圪
    -2.86
    蟊
    -2.86
    釭
    -2.80
     avec
    -2.78
    甞
    -2.77
    葑
    -2.69
    躄
    -2.66
    𓆸
    -2.63
    POSITIVE LOGITS
    The
    3.75
    There
    2.89
    .
    2.66
    If
    2.64
    $
    2.55
    It
    2.52
    大部分
    2.33
    如果你
    2.19
    ’
    2.17
    無論
    2.14
    Activations Density 0.002%

    No Known Activations