© 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. 130337
    Prev
    Next
    INDEX
    Explanations

    parses, imports, removes

    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
     인해
    -0.07
     devaluation
    -0.07
     лечение
    -0.07
    transform
    -0.06
     shuffle
    -0.06
    blend
    -0.06
    normalization
    -0.06
     skapa
    -0.06
     étape
    -0.06
     confounding
    -0.06
    POSITIVE LOGITS
     is
    0.07
     domeni
    0.06
    Convers
    0.06
    做事
    0.05
    articolo
    0.05
    পরিস
    0.05
     extant
    0.05
     Ventures
    0.05
    ????
    0.05
     हेल्
    0.05
    Activations Density 0.003%

    No Known Activations