© 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. 119334
    Prev
    Next
    INDEX
    Explanations

    linear algebra and analysis

    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
     יכול
    -0.07
     poate
    -0.06
     puedes
    -0.06
     может
    -0.06
     such
    -0.06
    ㅁ
    -0.06
    의
    -0.06
     puede
    -0.06
     कैसा
    -0.06
     конден
    -0.05
    POSITIVE LOGITS
    ちなみに
    0.07
     would
    0.07
     few
    0.06
     trouvé
    0.06
     wouldn
    0.06
     seraient
    0.06
     nondegenerate
    0.06
     सर्वात
    0.06
    রাং
    0.06
    ွား
    0.06
    Activations Density 0.002%

    No Known Activations