© 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. 119271
    Prev
    Next
    INDEX
    Explanations

    code namespaces

    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
    This
    -0.07
     স্কুলের
    -0.06
     ગા
    -0.06
     这个
    -0.06
     আলোচন
    -0.06
     が
    -0.06
     jeopardize
    -0.06
     یہ
    -0.06
     filled
    -0.06
     wypeł
    -0.06
    POSITIVE LOGITS
    :
    0.07
     살펴
    0.06
     অক্ষম
    0.06
     на
    0.06
    Prediction
    0.06
     अकेला
    0.06
     Quite
    0.06
     dif
    0.06
     क्वालीफ
    0.06
     Poly
    0.05
    Activations Density 0.014%

    No Known Activations