© 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. 22-GEMMASCOPE-RES-131K
    7. 72598
    Prev
    Next
    INDEX
    Explanations

    dates and names

    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_22/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
    <eos>
    -1.22
    *{-
    -1.00
     hedging
    -0.98
     négociations
    -0.96
    isine
    -0.94
    ほら
    -0.93
     alimentação
    -0.90
     shogun
    -0.90
     predetermin
    -0.90
    quivado
    -0.90
    POSITIVE LOGITS
     before
    1.07
     now
    0.94
    แล้ว
    0.91
     objekt
    0.88
     then
    0.84
    getClassName
    0.82
     methods
    0.80
     with
    0.79
    ##
    0.77
    이트
    0.77
    Activations Density 0.016%

    No Known Activations