© 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. 129346
    Prev
    Next
    INDEX
    Explanations

    sentence starters

    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
     možné
    -0.06
     आश्चर्य
    -0.06
     त्याने
    -0.06
     looked
    -0.06
     그런데
    -0.06
     hänen
    -0.06
    anggil
    -0.06
    looked
    -0.06
     μικ
    -0.05
     tamaños
    -0.05
    POSITIVE LOGITS
     attiva
    0.07
     অথবা
    0.07
     లేదా
    0.06
    욌
    0.06
     किंवा
    0.06
    <eos>
    0.06
     mínimo
    0.06
    minimum
    0.06
     untuk
    0.06
     Mar
    0.06
    Activations Density 0.003%

    No Known Activations