© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127974
    Prev
    Next
    INDEX
    Explanations

    step, contact

    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
     in
    -1.35
     from
    -1.30
     cocok
    -1.28
     it
    -1.23
     on
    -1.15
     to
    -1.13
    providedIn
    -1.13
     by
    -1.11
     альбом
    -1.08
    ॰
    -1.05
    POSITIVE LOGITS
     verminder
    1.09
     Propiedad
    1.02
     nuvem
    1.00
    modellen
    0.98
     dře
    0.98
    edipus
    0.97
     gericht
    0.95
    這些
    0.94
     nimmer
    0.94
     capables
    0.93
    Activations Density 0.001%

    No Known Activations