© 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. 72257
    Prev
    Next
    INDEX
    Explanations

    errors and failed operations

    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
    ﹔
    -1.24
     Pièces
    -1.07
     gena
    -1.07
     bakar
    -1.06
     apareció
    -1.05
     bendera
    -1.04
     angen
    -1.04
     polisi
    -1.03
     maaf
    -1.02
     damen
    -1.01
    POSITIVE LOGITS
    tolsó
    1.38
    ないです
    1.31
    EMENTS
    1.14
     didn
    1.13
    unków
    1.11
     don
    1.09
     unable
    1.08
    Debido
    1.08
     Мы
    1.07
     √
    1.07
    Activations Density 0.005%

    No Known Activations