© 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. 116612
    Prev
    Next
    INDEX
    Explanations

    a

    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
     seemingly
    -0.10
    它
    -0.07
     such
    -0.07
    🌜
    -0.06
     கடந்த
    -0.06
    seem
    -0.06
     inexplicable
    -0.06
    👫
    -0.06
    疵
    -0.06
    जेस्टिव
    -0.06
    POSITIVE LOGITS
     =
    0.07
     также
    0.07
     س
    0.06
     also
    0.06
     також
    0.06
    நாம
    0.06
     פ
    0.05
     también
    0.05
     também
    0.05
     스
    0.05
    Activations Density 0.007%

    No Known Activations