© 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. 14834
    Prev
    Next
    INDEX
    Explanations

    programming output and code inclusion

    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
     of
    -3.25
     that
    -2.67
     them
    -1.74
     who
    -1.73
     their
    -1.70
     its
    -1.59
     from
    -1.58
     includes
    -1.58
     whose
    -1.52
     decided
    -1.52
    POSITIVE LOGITS
    byes
    1.63
     Novembre
    1.55
    इटम
    1.54
    PLAUSE
    1.47
    lllllll
    1.47
    buster
    1.44
    llllllll
    1.44
    atürk
    1.43
     XXIV
    1.42
    wrights
    1.42
    Activations Density 0.016%

    No Known Activations