© 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. 128059
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities and absolute values

    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
    About
    -1.79
     {
    -1.71
    I
    -1.63
     Inex
    -1.59
     Neglect
    -1.57
    November
    -1.52
    about
    -1.51
    9
    -1.51
    гон
    -1.51
    begin
    -1.46
    POSITIVE LOGITS
     a
    1.95
    姤
    1.66
     more
    1.56
     creatively
    1.50
     localidades
    1.43
     sustent
    1.41
     comparatively
    1.41
     envió
    1.40
    checkable
    1.38
     premiere
    1.38
    Activations Density 0.011%

    No Known Activations