© 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. 116563
    Prev
    Next
    INDEX
    Explanations

    meteorologist, Hurricane Center, Wx Watch

    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
    的水
    -0.06
     स्थानीय
    -0.06
     někter
    -0.06
    日本では
    -0.06
     mengurangi
    -0.06
     giảm
    -0.06
     decrease
    -0.06
     স্থানীয়
    -0.06
     appropriate
    -0.06
     numa
    -0.06
    POSITIVE LOGITS
     relatif
    0.07
     remained
    0.07
     long
    0.06
     относительно
    0.06
     분석
    0.06
     totales
    0.06
    已经
    0.06
     prior
    0.06
     remain
    0.06
     મૂળ
    0.06
    Activations Density 0.004%

    No Known Activations