© 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. 40133
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by capitalized words

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

    So, elimination, now left with

    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
     एग्जाम्स
    0.41
    佟
    0.40
     varieg
    0.39
    这件事
    0.39
     curioso
    0.38
     কোন্‌
    0.38
     lézards
    0.38
    我自己
    0.38
     তুলনা
    0.37
     कॉले
    0.37
    POSITIVE LOGITS
    The
    0.66
     The
    0.59
    “
    0.58
     ‘’
    0.50
    There
    0.48
    ‘’
    0.48
     ‎
    0.47
     Основ
    0.46
     जिसमे
    0.46
     atleast
    0.46
    Activations Density 0.295%

    No Known Activations