© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60214
    Prev
    Next
    INDEX
    Explanations

    variable names

    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_10/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
    liegenden
    -1.75
     zestawie
    -1.55
     giocatore
    -1.52
     Nachmittag
    -1.52
    entwick
    -1.46
    每个
    -1.45
     Versuche
    -1.44
     Dienstag
    -1.43
     μας
    -1.43
    łec
    -1.41
    POSITIVE LOGITS
     who
    1.89
     precisa
    1.58
     hidupnya
    1.49
    )".
    1.48
    慊
    1.33
    
    1.33
    )'
    1.33
     can
    1.31
     while
    1.24
    他们在
    1.24
    Activations Density 0.068%

    No Known Activations