© 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. 128517
    Prev
    Next
    INDEX
    Explanations

    asking questions or starting code

    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
     पेड़
    -0.06
     كذلك
    -0.06
    chairman
    -0.06
     residential
    -0.06
     Exxon
    -0.06
     chairman
    -0.06
     Chairman
    -0.06
    ازه
    -0.06
     dilwale
    -0.06
    应急
    -0.06
    POSITIVE LOGITS
     четыре
    0.06
    sni
    0.06
     চিঠ
    0.06
     внутренних
    0.06
    imbang
    0.06
    four
    0.06
     quatrième
    0.06
    ended
    0.06
     four
    0.06
     Hunger
    0.06
    Activations Density 0.007%

    No Known Activations