© 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. 116511
    Prev
    Next
    INDEX
    Explanations

    during periods of injury

    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
     சிவப்பு
    -0.07
     fortn
    -0.07
    featuring
    -0.07
     secretive
    -0.06
    改变
    -0.06
    ändern
    -0.06
     boyhood
    -0.06
     unusual
    -0.06
    মাণ
    -0.06
    ពួកគេ
    -0.06
    POSITIVE LOGITS
     ต้อง
    0.07
     DURING
    0.07
     remaining
    0.06
     시간을
    0.06
     während
    0.06
     during
    0.06
    Remaining
    0.06
     timpul
    0.06
    実
    0.06
    救
    0.06
    Activations Density 0.051%

    No Known Activations