© 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. 118635
    Prev
    Next
    INDEX
    Explanations

    I want

    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
    鋃
    -0.07
    Examples
    -0.07
     ankaŭ
    -0.06
    dayspecial
    -0.06
    Also
    -0.06
     ধাতু
    -0.06
     również
    -0.06
     contoh
    -0.06
     регу
    -0.06
    ગા
    -0.06
    POSITIVE LOGITS
    -
    0.07
     তারা
    0.06
     rationally
    0.06
    rainer
    0.06
    とにかく
    0.06
     wide
    0.06
     reasonably
    0.06
     कलाकारों
    0.06
    诶
    0.06
    ᱼ
    0.05
    Activations Density 0.168%

    No Known Activations