© 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. 128228
    Prev
    Next
    INDEX
    Explanations

    points, runs, or innings

    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
     first
    -0.07
     fait
    -0.06
     notamment
    -0.06
     them
    -0.06
     Motors
    -0.06
     nicely
    -0.06
     brillant
    -0.05
     particularly
    -0.05
     sánh
    -0.05
     সর্বপ্রথম
    -0.05
    POSITIVE LOGITS
     FROM
    0.07
     because
    0.06
     unremarkable
    0.06
     diminished
    0.06
     salaire
    0.06
     UPDATE
    0.06
    шым
    0.06
    😵
    0.06
     ഒന്ന്
    0.06
    代表
    0.06
    Activations Density 0.008%

    No Known Activations