© 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. 128945
    Prev
    Next
    INDEX
    Explanations

    post, should, following, study, Is, Networks, Structure

    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
    ;
    -0.08
    を
    -0.07
    。
    -0.06
     вы
    -0.06
    При
    -0.06
    .
    -0.06
     using
    -0.06
     emprend
    -0.06
    の
    -0.06
    .;
    -0.06
    POSITIVE LOGITS
     ಸುರ
    0.06
    在哪里
    0.06
    例えば
    0.06
     STATE
    0.06
     изначально
    0.06
     brighter
    0.06
    ádio
    0.06
     Örneğin
    0.06
    itative
    0.06
     lonely
    0.05
    Activations Density 0.006%

    No Known Activations