© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119770
    Prev
    Next
    INDEX
    Explanations

    Attorney General

    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
     tabii
    -0.07
    ਨ੍ਹਾਂ
    -0.07
     wären
    -0.07
    ビデオ
    -0.07
     봐야
    -0.06
    جميع
    -0.06
    ٹوں
    -0.06
     શબ્
    -0.06
     moet
    -0.06
     eight
    -0.06
    POSITIVE LOGITS
     njega
    0.07
     oude
    0.07
    irlo
    0.06
    his
    0.06
    because
    0.06
     sehingga
    0.06
     чаще
    0.06
    Failure
    0.06
     because
    0.06
     όπου
    0.06
    Activations Density 0.001%

    No Known Activations