© 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. 22-GEMMASCOPE-RES-131K
    7. 38608
    Prev
    Next
    INDEX
    Explanations

    asking why

    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
    Поэтому
    -0.99
     satisfactory
    -0.99
     unexpected
    -0.98
     acceptable
    -0.96
    льности
    -0.92
     helped
    -0.92
     được
    -0.90
     properly
    -0.90
     finalmente
    -0.88
     vergessen
    -0.88
    POSITIVE LOGITS
    わざわざ
    1.42
     risking
    1.19
     risques
    1.18
     risk
    1.09
     RISK
    1.05
     such
    1.03
     KNOWN
    1.03
     risks
    1.01
    Risk
    1.01
     столь
    1.00
    Activations Density 0.053%

    No Known Activations