© 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. 130580
    Prev
    Next
    INDEX
    Explanations

    chemical alkyl and acyl groups

    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
    很大
    -0.06
     plentiful
    -0.06
    isValue
    -0.06
    尽可能
    -0.06
     malign
    -0.06
     surging
    -0.05
    ’
    -0.05
     mammoth
    -0.05
    argaan
    -0.05
    一種
    -0.05
    POSITIVE LOGITS
    เมื่อ
    0.06
     இருப்ப
    0.06
    全体
    0.06
     différents
    0.06
     since
    0.06
    ものが
    0.06
    anno
    0.06
     आध्यात्म
    0.06
    தன
    0.06
     καθώς
    0.06
    Activations Density 0.031%

    No Known Activations