© 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. 116681
    Prev
    Next
    INDEX
    Explanations

    code blocks and declarations like const, struct, var

    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
     so
    -0.07
     необходимости
    -0.07
     ತೆಗೆ
    -0.06
     آسی
    -0.06
    क्ष
    -0.06
     Stabil
    -0.06
    Transforms
    -0.06
     nevoie
    -0.06
     that
    -0.06
    Remove
    -0.06
    POSITIVE LOGITS
     különböz
    0.07
     meist
    0.07
     significativa
    0.06
     significative
    0.06
     elaboration
    0.06
    就连
    0.06
                  
    0.06
    🌨
    0.06
     제외
    0.06
     почина
    0.06
    Activations Density 0.002%

    No Known Activations