© 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. 14146
    Prev
    Next
    INDEX
    Explanations

    power sources and forces

    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
    '
    -1.89
     time
    -1.84
    ."
    -1.68
     decorados
    -1.55
    carnated
    -1.55
     it
    -1.53
    "
    -1.47
     estremamente
    -1.47
     having
    -1.45
    !
    -1.45
    POSITIVE LOGITS
    僦
    1.88
     The
    1.85
     subtleties
    1.72
    不愧
    1.68
    Itz
    1.63
    AutoresizingMask
    1.60
     pout
    1.56
    揠
    1.55
     場面
    1.55
     более
    1.54
    Activations Density 0.002%

    No Known Activations