© 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. 120130
    Prev
    Next
    INDEX
    Explanations

    official events

    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
     இவரது
    -0.07
    <u>
    -0.07
     его
    -0.06
    problems
    -0.06
     fisheries
    -0.06
     popular
    -0.06
     उसका
    -0.06
     attractions
    -0.06
     আসে
    -0.06
     emph
    -0.06
    POSITIVE LOGITS
     sappiamo
    0.06
    Hear
    0.06
    成本
    0.06
    த்துக்கும்
    0.06
     이전
    0.06
     our
    0.06
     previstas
    0.06
    ﾝ
    0.06
     самых
    0.06
     !***
    0.06
    Activations Density 0.081%

    No Known Activations