© 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. 120760
    Prev
    Next
    INDEX
    Explanations

    filter by condition

    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
    шість
    -0.07
    確實
    -0.06
    确实
    -0.06
    currentState
    -0.06
     you
    -0.06
    ampaikan
    -0.06
     ইহাতে
    -0.06
     mitigation
    -0.06
     মালা
    -0.06
     four
    -0.06
    POSITIVE LOGITS
     cerca
    0.07
     Filtr
    0.07
     Filter
    0.07
     filtr
    0.06
    滤
    0.06
     bapt
    0.06
    filtr
    0.06
     filtro
    0.06
     करतो
    0.06
     aproximadamente
    0.06
    Activations Density 0.007%

    No Known Activations