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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70232
    Prev
    Next
    INDEX
    Explanations

    expressions of thanks

    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
    蟜
    -2.19
     a
    -2.06
     is
    -1.99
     be
    -1.95
    を行
    -1.93
    五日
    -1.86
     gewisser
    -1.78
     --
    -1.77
    ⚋
    -1.77
    想起
    -1.75
    POSITIVE LOGITS
    0
    2.17
    .
    2.05
    >
    1.96
    From
    1.87
    从来没有
    1.83
    Since
    1.81
    transQ
    1.77
    which
    1.77
    Though
    1.71
    Although
    1.69
    Activations Density 0.003%

    No Known Activations