© 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. 129086
    Prev
    Next
    INDEX
    Explanations

    json, js, response

    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
     எல்லோ
    -0.07
    菄
    -0.07
     przed
    -0.07
     eliminación
    -0.06
     masquer
    -0.06
     گاه
    -0.06
    acao
    -0.06
    roups
    -0.06
     Naked
    -0.06
    PostBody
    -0.06
    POSITIVE LOGITS
     all
    0.06
    その後
    0.06
    Aux
    0.06
    为止
    0.05
    我
    0.05
    Default
    0.05
    4
    0.05
     সপ্তাহের
    0.05
    Misc
    0.05
    Hooks
    0.05
    Activations Density 0.003%

    No Known Activations