© 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. 64740
    Prev
    Next
    INDEX
    Explanations

    declaration after variable

    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
    鬟
    -1.28
    bufio
    -1.11
    lampen
    -1.09
    itieren
    -1.07
    yorum
    -1.04
    standen
    -1.02
    wachs
    -1.02
    hafter
    -1.02
     Tämä
    -1.01
    songs
    -1.00
    POSITIVE LOGITS
     levering
    1.09
     gegebenen
    1.05
    ;">
    1.05
     LECT
    1.02
    えっ
    1.00
     Saltar
    0.97
     unterstüt
    0.97
     bearbeitet
    0.95
    、『
    0.94
     entgeg
    0.94
    Activations Density 0.012%

    No Known Activations