© 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. 117214
    Prev
    Next
    INDEX
    Explanations

    mechanical or physical forces

    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
     ispit
    -0.06
    पह
    -0.06
    也
    -0.06
     also
    -0.06
     combined
    -0.06
    烏
    -0.06
     Rauch
    -0.06
    茶
    -0.06
     Also
    -0.06
     també
    -0.06
    POSITIVE LOGITS
    ネック
    0.07
     благоприят
    0.06
     routinely
    0.06
     incumbents
    0.06
     continuamente
    0.06
    (~
    0.06
     petitions
    0.06
     decisões
    0.06
     ежедневно
    0.06
    ლებ
    0.06
    Activations Density 0.011%

    No Known Activations