© 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. 128257
    Prev
    Next
    INDEX
    Explanations

    court filings and submissions

    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
     sometimes
    -0.08
    sometimes
    -0.08
    有时候
    -0.07
     گاه
    -0.07
     Often
    -0.07
    某些
    -0.07
     σύμφωνα
    -0.07
    often
    -0.07
     often
    -0.07
     Sometimes
    -0.07
    POSITIVE LOGITS
     this
    0.08
    unuz
    0.06
     этого
    0.06
     لهذا
    0.06
     этому
    0.06
     tohoto
    0.05
     αυτή
    0.05
     होके
    0.05
     بهذا
    0.05
     ನಮ್ಮ
    0.05
    Activations Density 0.006%

    No Known Activations