© 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. 128061
    Prev
    Next
    INDEX
    Explanations

    Prognostic significance

    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
     horrible
    -0.07
     terrible
    -0.07
     terrific
    -0.07
     you
    -0.06
     funny
    -0.06
     terrib
    -0.06
     comical
    -0.06
     yellow
    -0.06
     hideous
    -0.06
    ysis
    -0.06
    POSITIVE LOGITS
     통해
    0.07
     amidst
    0.06
     yksi
    0.06
     definito
    0.06
    に戻
    0.06
     فونبٹ
    0.06
    တွင်
    0.06
     أيضاً
    0.06
     μία
    0.06
     eTo
    0.06
    Activations Density 0.001%

    No Known Activations