© 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. 72725
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     hodně
    -0.89
    сі
    -0.88
     Polity
    -0.86
     lately
    -0.85
    fillText
    -0.80
    んの
    -0.79
    ibt
    -0.78
    
    -0.76
    でん
    -0.76
    onames
    -0.75
    POSITIVE LOGITS
     (_.
    0.81
    ᱷ
    0.80
    即可
    0.80
    sendLog
    0.79
     могла
    0.79
     resembled
    0.77
    ᵗ
    0.77
    回転
    0.76
    gsl
    0.76
    thée
    0.76
    Activations Density 0.022%

    No Known Activations