© 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. 116677
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols followed by technical terms

    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
     इंट्रो
    -0.07
     on
    -0.07
     daqu
    -0.07
     Those
    -0.07
     twenty
    -0.07
     for
    -0.06
     eleven
    -0.06
     When
    -0.06
     făcut
    -0.06
    Those
    -0.06
    POSITIVE LOGITS
    isha
    0.06
     navig
    0.06
     হেফাজতে
    0.06
    azar
    0.05
     المنطقة
    0.05
     резулта
    0.05
     weathered
    0.05
     realizar
    0.05
     workable
    0.05
     رمز
    0.05
    Activations Density 0.022%

    No Known Activations