© 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. 128751
    Prev
    Next
    INDEX
    Explanations

    registered as, paved trails, extent of

    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
     disait
    -1.10
    怎么能
    -1.08
     in
    -1.04
     Vorteil
    -1.01
    文分享
    -1.00
     bezpośrednio
    -0.96
     récompense
    -0.95
     slipped
    -0.94
     supuestamente
    -0.94
     daardoor
    -0.93
    POSITIVE LOGITS
     and
    1.95
    </h4>
    1.21
    </h3>
    1.11
    ̀
    0.95
     și
    0.95
    Bibliografie
    0.95
    ICOLON
    0.94
    tement
    0.94
    ſus
    0.94
    ginous
    0.94
    Activations Density 0.042%

    No Known Activations