© 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. 73614
    Prev
    Next
    INDEX
    Explanations

    JSON object

    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
     in
    -1.83
     of
    -1.59
     by
    -1.38
     using
    -1.13
     through
    -1.05
    落的
    -1.03
    枇
    -0.98
     ver
    -0.98
     like
    -0.97
    自身的
    -0.96
    POSITIVE LOGITS
     Affaires
    1.41
    웅
    1.37
    liana
    1.32
    renowned
    1.30
     constitue
    1.30
    明日は
    1.28
    provides
    1.27
    鳚
    1.26
    ąp
    1.25
     мечты
    1.25
    Activations Density 0.094%

    No Known Activations