© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21923
    Prev
    Next
    INDEX
    Explanations

    technical question introductions

    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
    Despite
    -2.23
     These
    -2.19
    //
    -2.14
    ࿙
    -2.14
     Despite
    -2.11
     There
    -2.09
     from
    -2.08
    呜呜
    -2.06
     They
    -2.05
    P
    -2.05
    POSITIVE LOGITS
    茈
    2.83
    撂
    2.64
     he
    2.64
    部分が
    2.61
     нового
    2.47
    橚
    2.42
    搋
    2.42
    ”-
    2.36
     superb
    2.34
     famed
    2.34
    Activations Density 0.000%

    No Known Activations