© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 127922
    Prev
    Next
    INDEX
    Explanations

    said "

    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
    Negative Logits
    VALID
    -0.06
    ASK
    -0.06
     основания
    -0.06
     wahr
    -0.06
    Democratic
    -0.06
     reciprocal
    -0.06
     γλώ
    -0.06
    树
    -0.05
     रास्ते
    -0.05
     অন্যদের
    -0.05
    POSITIVE LOGITS
     없이
    0.08
     without
    0.07
     zonder
    0.07
     સામાન્ય
    0.07
     senza
    0.07
     normally
    0.07
     χωρίς
    0.07
     ordinarily
    0.07
     Besides
    0.06
     diez
    0.06
    Activations Density 0.019%

    No Known Activations