© 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. 119439
    Prev
    Next
    INDEX
    Explanations

    projects utilizing resources

    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
    रू
    -0.07
    ابقه
    -0.06
    śród
    -0.06
    кість
    -0.06
    ড়ান্ত
    -0.06
     近
    -0.06
     ठोस
    -0.06
     codified
    -0.06
     பாரம்பரிய
    -0.06
    లన
    -0.05
    POSITIVE LOGITS
     come
    0.07
    come
    0.07
     because
    0.07
     just
    0.07
     in
    0.06
     decently
    0.06
    因为
    0.06
     допъл
    0.06
     comes
    0.06
     into
    0.06
    Activations Density 0.001%

    No Known Activations