© 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. 129308
    Prev
    Next
    INDEX
    Explanations

    stainless steel

    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
     supplémentaire
    -0.07
     spacious
    -0.07
     supplémentaires
    -0.06
     overcrowded
    -0.06
     revamped
    -0.06
     cramped
    -0.06
    intersects
    -0.06
    ঢ
    -0.06
    Flat
    -0.06
     slab
    -0.06
    POSITIVE LOGITS
     Aralık
    0.07
     통해서
    0.06
     legale
    0.06
     comparisons
    0.06
     Soren
    0.06
    の結果
    0.06
    がいい
    0.06
     décembre
    0.06
    latest
    0.06
     য
    0.06
    Activations Density 0.023%

    No Known Activations