© 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. 128045
    Prev
    Next
    INDEX
    Explanations

    copyright year followed by 0

    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
     gebruiken
    -0.06
     готовы
    -0.06
     لینا
    -0.06
     хотят
    -0.06
     ఉపయోగ
    -0.06
    ainer
    -0.06
     behöver
    -0.06
    古典
    -0.06
    اویز
    -0.06
     используют
    -0.06
    POSITIVE LOGITS
     an
    0.07
     unrival
    0.07
     evolving
    0.06
     a
    0.06
     unrivalled
    0.06
     varying
    0.06
     immaculate
    0.06
     upon
    0.06
     ஏற்படுகிறது
    0.06
     চতু
    0.05
    Activations Density 0.010%

    No Known Activations