© 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. 129665
    Prev
    Next
    INDEX
    Explanations

    since a year

    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
     முதலிய
    -0.07
     ξεκ
    -0.07
     igualmente
    -0.07
    開啟
    -0.07
     inició
    -0.07
     آغاز
    -0.07
     시작
    -0.07
     zač
    -0.07
    inizio
    -0.07
    ちょうど
    -0.07
    POSITIVE LOGITS
     future
    0.07
    with
    0.06
     both
    0.06
     ",
    0.06
     with
    0.06
     اہم
    0.06
     important
    0.06
     whose
    0.06
     futura
    0.06
     फार्म
    0.06
    Activations Density 0.019%

    No Known Activations