© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130540
    Prev
    Next
    INDEX
    Explanations

    measure and distributions

    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
     pry
    -0.06
    पत्र
    -0.06
    adan
    -0.06
     distinction
    -0.06
     Luck
    -0.06
    Void
    -0.05
     rollback
    -0.05
    াসন
    -0.05
     Ethn
    -0.05
     இறுதி
    -0.05
    POSITIVE LOGITS
     könnten
    0.07
    reasonably
    0.07
     könnte
    0.07
    basically
    0.07
     famosa
    0.07
     podría
    0.06
     potrebbero
    0.06
     প্রয়োজনীয়
    0.06
     ಮೂಲ
    0.06
    基本上
    0.06
    Activations Density 0.002%

    No Known Activations