© 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. 22-GEMMASCOPE-RES-131K
    7. 11237
    Prev
    Next
    INDEX
    Explanations

    subscripts or formulas

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

    scientific notation with subscripts, particularly in mathematical or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    があり
    -1.51
     kleid
    -1.44
     necesitaba
    -1.39
    berapa
    -1.38
     the
    -1.38
     in
    -1.37
     возможность
    -1.34
     Biografie
    -1.34
     erns
    -1.31
    膿
    -1.30
    POSITIVE LOGITS
    新しく
    1.66
    P
    1.53
    5
    1.49
    6
    1.48
    M
    1.48
    c
    1.47
    O
    1.47
    V
    1.44
    还得
    1.44
     {
    1.43
    Activations Density 0.016%

    No Known Activations