© 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. 119954
    Prev
    Next
    INDEX
    Explanations

    failure and errors

    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
     தாண்ட
    -0.07
     NOT
    -0.06
    되지
    -0.06
     dilihat
    -0.06
     नहीं
    -0.06
     മികച്ച
    -0.06
     attravers
    -0.06
     donnant
    -0.06
     boli
    -0.06
     samurai
    -0.06
    POSITIVE LOGITS
     previously
    0.06
    itism
    0.06
    rusty
    0.06
    ictured
    0.06
    后再
    0.06
     would
    0.06
    केंद्र
    0.06
     bunny
    0.06
    நிலையில்
    0.06
     Flax
    0.06
    Activations Density 0.001%

    No Known Activations