© 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. 120427
    Prev
    Next
    INDEX
    Explanations

    XML attributes and code syntax

    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
     равен
    -0.06
    帆
    -0.06
     イヤ
    -0.06
     Detection
    -0.06
     و
    -0.06
     detection
    -0.06
     וכ
    -0.06
     हराया
    -0.05
    POSITIVE LOGITS
     by
    0.08
     in
    0.07
    directly
    0.06
     at
    0.06
     apparten
    0.06
    在
    0.06
     pelt
    0.06
     material
    0.06
    !;
    0.06
    there
    0.06
    Activations Density 0.005%

    No Known Activations