© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116720
    Prev
    Next
    INDEX
    Explanations

    Q:, An, High, CCC

    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
    कप्तान
    -0.06
     پس
    -0.06
     ي
    -0.06
    ö
    -0.06
     дети
    -0.06
     selben
    -0.06
     sugest
    -0.06
     सटीक
    -0.06
     बेहतर
    -0.06
    คือ
    -0.06
    POSITIVE LOGITS
     twos
    0.06
    ardır
    0.06
     whose
    0.05
    如果是
    0.05
    違う
    0.05
     zigzag
    0.05
    它们的
    0.05
     új
    0.05
    也都
    0.05
    ERR
    0.05
    Activations Density 0.001%

    No Known Activations