© 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. 117473
    Prev
    Next
    INDEX
    Explanations

    clock rate

    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
    codingPath
    -0.06
     BCCI
    -0.06
    anium
    -0.06
     Colson
    -0.06
     December
    -0.06
     بابەت
    -0.06
     ધર
    -0.05
     segala
    -0.05
     ഇത്
    -0.05
    امام
    -0.05
    POSITIVE LOGITS
     चिह्न
    0.07
     ग्रेड
    0.07
    Grade
    0.06
     ऑप्शन
    0.06
     already
    0.06
     état
    0.06
    careers
    0.06
     영어
    0.06
     একদম
    0.06
    जार
    0.06
    Activations Density 0.027%

    No Known Activations