© 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. 119324
    Prev
    Next
    INDEX
    Explanations

    copyright notice

    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
    liess
    -0.07
    數字
    -0.07
     steroids
    -0.06
    いましたが
    -0.06
     but
    -0.06
    انیہ
    -0.06
    颼
    -0.06
     каждого
    -0.06
     ஆனால்
    -0.06
     тепер
    -0.06
    POSITIVE LOGITS
    这类
    0.08
     ,
    0.07
    <strong>
    0.06
    拥有
    0.06
    such
    0.06
     such
    0.06
    upart
    0.06
    ，
    0.06
     THINGS
    0.06
     maxi
    0.05
    Activations Density 0.001%

    No Known Activations