© 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. 129238
    Prev
    Next
    INDEX
    Explanations

    numbers in equations

    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
    K
    -0.06
    <eos>
    -0.06
    J
    -0.06
     상
    -0.06
    .)
    -0.05
     ແ
    -0.05
    acey
    -0.05
    R
    -0.05
     that
    -0.05
     need
    -0.05
    POSITIVE LOGITS
     برخی
    0.07
     erity
    0.07
     частично
    0.07
     kıs
    0.06
     especiales
    0.06
     уровень
    0.06
     विशेष
    0.06
     exempt
    0.06
    ρές
    0.06
     мисте
    0.06
    Activations Density 0.002%

    No Known Activations