© 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. 118195
    Prev
    Next
    INDEX
    Explanations

    stores, workers, councillors, members

    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
    );
    -0.06
     specifically
    -0.06
     using
    -0.06
    ),
    -0.06
     թվական
    -0.05
     ద్వారా
    -0.05
     from
    -0.05
     as
    -0.05
     during
    -0.05
     ({
    -0.05
    POSITIVE LOGITS
    Otro
    0.07
     až
    0.07
     vemos
    0.07
    បន្ទ
    0.07
     tổ
    0.07
     hacia
    0.07
     ۳
    0.06
    款
    0.06
    जारत
    0.06
     astonishing
    0.06
    Activations Density 0.020%

    No Known Activations