© 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. 25219
    Prev
    Next
    INDEX
    Explanations

    categories and lists of entities

    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
     bambu
    -1.21
     alip
    -1.16
     those
    -1.15
     anivers
    -1.14
     megane
    -1.09
     parlament
    -1.09
     revisor
    -1.06
     conster
    -1.05
     menyen
    -1.04
     taba
    -1.04
    POSITIVE LOGITS
    <eos>
    1.13
     trám
    1.13
     pensamientos
    1.09
    ünd
    1.08
    ată
    1.06
     Отечественной
    1.04
    donde
    1.02
     że
    1.02
    yecek
    1.02
     IELTS
    0.99
    Activations Density 0.008%

    No Known Activations