© 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. 129216
    Prev
    Next
    INDEX
    Explanations

    times and durations

    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
    午後
    -0.07
     إص
    -0.06
    owntown
    -0.06
     오전
    -0.06
    午前
    -0.06
    typically
    -0.06
     午前
    -0.06
    hoog
    -0.06
     낮
    -0.06
    !;
    -0.06
    POSITIVE LOGITS
     broader
    0.06
    fle
    0.06
     wohl
    0.06
    ανο
    0.06
    nto
    0.06
     wider
    0.06
    ಾರ್ಥ
    0.06
     comenzaron
    0.06
     permitem
    0.06
     useful
    0.06
    Activations Density 0.007%

    No Known Activations