© 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. 124928
    Prev
    Next
    INDEX
    Explanations

    lists expectations and data

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

    performance and technical terms

    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
    مسه
    0.51
     Im
    0.49
     unclean
    0.48
    મિક
    0.47
    もっと
    0.47
    ्रिक
    0.46
    롤
    0.46
     حی
    0.45
    介護
    0.45
    asciiPanel
    0.44
    POSITIVE LOGITS
     Народ
    0.59
    Iterator
    0.49
    Notes
    0.49
    Buzz
    0.48
    igns
    0.47
    Descending
    0.47
     Первая
    0.46
    ITT
    0.46
     Вол
    0.46
    ానని
    0.46
    Activations Density 0.000%

    No Known Activations