© 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. 67502
    Prev
    Next
    INDEX
    Explanations

    operations involving subtraction

    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
    {
    -2.39
     отличаются
    -2.38
     This
    -2.33
     was
    -2.28
     –
    -2.19
     Kanton
    -2.17
     Etik
    -2.14
     kelahiran
    -2.13
    小子
    -2.11
    ../../../
    -2.06
    POSITIVE LOGITS
    ).
    2.95
    ୌ
    2.64
     unleash
    2.58
    ⽌
    2.56
    を設置
    2.44
    镲
    2.42
    LayoutConstraint
    2.33
     handful
    2.27
    钿
    2.27
    .
    2.13
    Activations Density 0.006%

    No Known Activations