© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 65017
    Prev
    Next
    INDEX
    Explanations

    numbers and amounts

    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_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
     bezit
    -1.16
     possu
    -1.14
    arrête
    -1.09
     obtend
    -1.09
     ocorrer
    -1.07
     conseguiu
    -1.07
    Agencia
    -1.02
     debió
    -1.01
    收购
    -1.01
     poderá
    -1.01
    POSITIVE LOGITS
     and
    1.30
     for
    1.23
    SE
    1.07
     to
    1.03
     with
    1.02
    }-\
    1.01
     some
    0.97
    7
    0.95
    Math
    0.94
    "{\
    0.92
    Activations Density 0.029%

    No Known Activations