© 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. 116357
    Prev
    Next
    INDEX
    Explanations

    game titles and topics

    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
    部は
    -0.07
     можна
    -0.06
     från
    -0.06
    इकिल
    -0.06
    杽
    -0.06
    อส
    -0.06
     можно
    -0.06
    ../../../
    -0.06
    するのが
    -0.05
    ConsoleText
    -0.05
    POSITIVE LOGITS
    new
    0.07
     redesigned
    0.07
     Injury
    0.06
     new
    0.06
     reaction
    0.06
     spectacular
    0.06
     injury
    0.06
     பாதுகாப்பு
    0.06
     ubiquitous
    0.06
     तमाम
    0.06
    Activations Density 0.007%

    No Known Activations