© 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. 119752
    Prev
    Next
    INDEX
    Explanations

    Endovascular, Japanese, Breeders' Cup

    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
    :
    -0.07
     #
    -0.06
     camaraderie
    -0.06
     studies
    -0.06
     “
    -0.06
     incredible
    -0.06
     kines
    -0.05
     中
    -0.05
     conducted
    -0.05
     quiescent
    -0.05
    POSITIVE LOGITS
     déjà
    0.07
     Biographie
    0.07
    ందం
    0.07
     histoire
    0.06
    Annual
    0.06
     materiales
    0.06
     이미
    0.06
     تاریخ
    0.06
     öffent
    0.06
     භාවිත
    0.06
    Activations Density 0.001%

    No Known Activations