© 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. 67351
    Prev
    Next
    INDEX
    Explanations

    scale derivatives and cell contexts

    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
    There
    -2.14
    Usually
    -2.11
    Going
    -2.09
    Sometimes
    -2.03
    Often
    -1.99
    Perhaps
    -1.94
    Many
    -1.91
    rmtree
    -1.91
    Being
    -1.89
    Every
    -1.85
    POSITIVE LOGITS
    ’
    2.13
     also
    1.73
    ကိုးက
    1.58
     —
    1.57
    er
    1.57
    尛
    1.54
    ものに
    1.52
     innan
    1.51
     dizaines
    1.49
    ,’
    1.48
    Activations Density 0.001%

    No Known Activations