© 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. 128224
    Prev
    Next
    INDEX
    Explanations

    county, district, town, seat

    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
    zub
    -0.06
    certain
    -0.06
    zek
    -0.05
     ,
    -0.05
    AX
    -0.05
     Chaos
    -0.05
     meager
    -0.05
    दूर
    -0.05
    Neutral
    -0.05
    ES
    -0.05
    POSITIVE LOGITS
     모두
    0.07
     WeChat
    0.07
     Karachi
    0.06
     tačiau
    0.06
     funziona
    0.06
     विडियो
    0.06
     wajah
    0.06
     thèse
    0.06
     mohou
    0.06
     zove
    0.06
    Activations Density 0.004%

    No Known Activations