© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 27391
    Prev
    Next
    INDEX
    Explanations

    Black Flex, patients you

    np_acts-logits-general · gemini-2.5-flash-lite

    cold temperatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     студент
    0.49
     logement
    0.47
    ществует
    0.46
     programmatic
    0.45
    딨
    0.45
    る
    0.45
     வெப்சீரி
    0.44
     reservation
    0.43
     Jamie
    0.43
     Westinghouse
    0.43
    POSITIVE LOGITS
    felder
    0.49
    COMING
    0.49
    ೊಳ
    0.48
    QA
    0.48
    had
    0.47
    撿
    0.47
    coming
    0.47
    Delete
    0.46
    qa
    0.46
    choose
    0.46
    Activations Density 0.000%

    No Known Activations