© 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. 42037
    Prev
    Next
    INDEX
    Explanations

    totally + various words

    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
     ваз
    -2.39
    ܇
    -2.36
     erns
    -2.36
     på
    -2.34
    いい
    -2.27
    I
    -2.20
    </i>
    -2.20
    接近
    -2.19
    u
    -2.19
     епи
    -2.17
    POSITIVE LOGITS
    所以我
    2.13
    甡
    2.08
    話は
    2.03
     was
    1.98
    敉
    1.97
     terwijl
    1.95
    这样一个
    1.95
     ナビ
    1.89
    が多
    1.88
    tively
    1.88
    Activations Density 0.003%

    No Known Activations