© 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. 116966
    Prev
    Next
    INDEX
    Explanations

    output file

    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
    适合
    -0.06
    蛳
    -0.06
     vhodné
    -0.06
     suficiente
    -0.06
     Marine
    -0.06
     ততই
    -0.06
     scientific
    -0.06
     Orphan
    -0.06
     marine
    -0.06
    科学
    -0.06
    POSITIVE LOGITS
     conversations
    0.07
     Calculations
    0.06
     Hussein
    0.06
     Cowboys
    0.06
     Conversations
    0.06
     granule
    0.06
     croup
    0.06
     capucha
    0.06
     Oslo
    0.05
     Combination
    0.05
    Activations Density 0.002%

    No Known Activations