© 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. 120857
    Prev
    Next
    INDEX
    Explanations

    ranges and bins

    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
     massive
    -0.08
     enormous
    -0.08
     famed
    -0.07
     огром
    -0.07
     an
    -0.07
     huge
    -0.07
     ogrom
    -0.07
     tremendous
    -0.07
     రాష్ట్ర
    -0.06
     video
    -0.06
    POSITIVE LOGITS
     interval
    0.07
     analyzers
    0.07
     intervals
    0.07
    intervals
    0.07
     inequalities
    0.06
     구간
    0.06
     creatinine
    0.06
     intervalo
    0.06
     हेल्थ
    0.06
     intervalles
    0.06
    Activations Density 0.007%

    No Known Activations