© 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. 117194
    Prev
    Next
    INDEX
    Explanations

    ${ and }}

    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
     a
    -0.06
     Jardin
    -0.06
     usw
    -0.06
    return
    -0.06
    ...";
    -0.06
     intentional
    -0.05
    ...");
    -0.05
    手続き
    -0.05
     comme
    -0.05
     joyous
    -0.05
    POSITIVE LOGITS
     empez
    0.06
     Matches
    0.06
     Regarding
    0.06
     Visiting
    0.06
     вместо
    0.06
    因而
    0.06
     더
    0.06
     dunque
    0.06
    erste
    0.06
     Instead
    0.06
    Activations Density 0.005%

    No Known Activations