© 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. 34-GEMMASCOPE-RES-131K
    7. 92983
    Prev
    Next
    INDEX
    Explanations

    physical enclosures

    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_34/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
     sowie
    -1.26
    以及
    -1.03
     needed
    -1.02
     enthalten
    -1.00
     notamment
    -0.98
    в
    -0.95
     involved
    -0.94
    Vin
    -0.94
     a
    -0.94
     however
    -0.90
    POSITIVE LOGITS
     that
    1.52
     visiter
    0.99
     ){
    0.99
     which
    0.99
     podes
    0.95
     tirs
    0.94
    başı
    0.94
     bébé
    0.93
     liten
    0.93
    ˣ
    0.93
    Activations Density 0.205%

    No Known Activations