© 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. 26275
    Prev
    Next
    INDEX
    Explanations

    programming language identifiers

    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
     with
    -1.52
     any
    -1.25
    が
    -1.18
     by
    -1.17
     only
    -1.13
     solely
    -1.02
     ironically
    -1.02
     under
    -1.01
    ™
    -1.00
     just
    -0.99
    POSITIVE LOGITS
    際には
    1.14
     paramètres
    1.12
    様な
    1.09
     طو
    1.06
     levering
    1.05
    不高
    1.04
     angeschlossen
    1.03
    ฌ
    1.02
    รม
    1.01
     chén
    1.01
    Activations Density 0.034%

    No Known Activations