© 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. 116621
    Prev
    Next
    INDEX
    Explanations

    Assembly attributes and declarations

    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
    ;
    -0.07
     exceedingly
    -0.06
     reasonably
    -0.06
     establish
    -0.06
     obtain
    -0.06
     provides
    -0.06
    .;
    -0.06
     sufficient
    -0.06
     establishing
    -0.06
    POSITIVE LOGITS
    Subject
    0.06
     ஷ
    0.06
     ను
    0.06
     Subject
    0.06
    ຜະລິດຕ
    0.06
    すべての
    0.05
     podob
    0.05
    subject
    0.05
    মন্ত্র
    0.05
    शिला
    0.05
    Activations Density 0.005%

    No Known Activations