© 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. 117122
    Prev
    Next
    INDEX
    Explanations

    URLs, file paths, or code comments

    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
     efectu
    -0.07
    ...",
    -0.06
    ...");
    -0.06
    他们
    -0.06
     accompanying
    -0.06
     przeprowad
    -0.06
     उन्हें
    -0.06
    使其
    -0.06
    images
    -0.06
     efectuar
    -0.06
    POSITIVE LOGITS
    国道
    0.07
     TripAdvisor
    0.06
     the
    0.06
     adrenalin
    0.06
    려면
    0.06
     గత
    0.06
    pinterest
    0.06
    rick
    0.06
     बहस
    0.06
     misalnya
    0.06
    Activations Density 0.003%

    No Known Activations