© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130375
    Prev
    Next
    INDEX
    Explanations

    javascript code or symbols

    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
    モダン
    -0.07
     transgress
    -0.06
     が
    -0.06
     ...,
    -0.06
    ـــ
    -0.05
     totalling
    -0.05
     مرحله
    -0.05
     рассчита
    -0.05
     getTotal
    -0.05
    ҷ
    -0.05
    POSITIVE LOGITS
     new
    0.07
     to
    0.07
     of
    0.07
     Elle
    0.06
     църква
    0.06
     elle
    0.06
     Kale
    0.06
     она
    0.06
    лица
    0.06
    เธอ
    0.06
    Activations Density 0.001%

    No Known Activations