© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117505
    Prev
    Next
    INDEX
    Explanations

    fighting resistance and battles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aggression
    -0.06
    ीकरण
    -0.06
     impressive
    -0.06
     fierce
    -0.06
     qo
    -0.06
     will
    -0.06
    Shar
    -0.06
     murderous
    -0.06
     ferocious
    -0.06
     sharply
    -0.06
    POSITIVE LOGITS
     Stephen
    0.06
     railroad
    0.06
     died
    0.06
     presiden
    0.06
    ченко
    0.06
    ASHINGTON
    0.06
     richesse
    0.06
     Ferrari
    0.06
     대통령
    0.06
    वैज्ञानिक
    0.06
    Activations Density 0.011%

    No Known Activations