© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98470
    Prev
    Next
    INDEX
    Explanations

    #include <...>.h or .cl

    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
     schlafen
    -1.19
    おわりに
    -1.19
    YSTEM
    -1.17
     a
    -1.11
    好好的
    -1.10
    _;
    -1.04
     plaît
    -1.03
    를
    -1.03
     größe
    -1.03
    wakili
    -1.02
    POSITIVE LOGITS
    arching
    1.15
     SEVENT
    1.13
    prech
    1.09
     ISRAEL
    1.04
    vamo
    1.03
     HUND
    1.02
     marts
    1.02
    Denne
    1.02
     TWENTY
    1.01
    ここでは
    1.00
    Activations Density 0.098%

    No Known Activations