© 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. 14436
    Prev
    Next
    INDEX
    Explanations

    special characters and extensions

    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
    -
    -2.38
     when
    -2.23
     a
    -1.92
    t
    -1.88
    f
    -1.87
     in
    -1.80
     to
    -1.77
     can
    -1.76
    1
    -1.75
    c
    -1.69
    POSITIVE LOGITS
    rivit
    2.09
    cích
    1.91
    ritsar
    1.89
    gensen
    1.82
    ˗
    1.78
    ???????
    1.76
    êmio
    1.76
    ichtete
    1.75
    ablemente
    1.74
    año
    1.72
    Activations Density 0.020%

    No Known Activations