© 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. 14308
    Prev
    Next
    INDEX
    Explanations

    parent "

    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
     the
    -2.28
     amazingly
    -1.73
    罍
    -1.72
     strikingly
    -1.69
     remarkably
    -1.68
    -
    -1.66
     unbelievably
    -1.66
     vários
    -1.66
     \&
    -1.65
    called
    -1.63
    POSITIVE LOGITS
    0
    1.93
    6
    1.85
    4
    1.79
     Those
    1.79
    ⅜
    1.77
    These
    1.77
     Probably
    1.73
    ⅞
    1.69
    zzlement
    1.69
    3
    1.66
    Activations Density 0.026%

    No Known Activations