© 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. 96100
    Prev
    Next
    INDEX
    Explanations

    end of phrase punctuation

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

    available to

    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
    ל
    0.49
     ہے
    0.48
     серьез
    0.47
    คุณ
    0.46
     এলাকায়
    0.46
    诗
    0.46
     এলাকায়
    0.45
    附近
    0.45
    标题
    0.45
    湪
    0.45
    POSITIVE LOGITS
    .\
    0.62
    。
    0.60
    .\\
    0.55
    ។
    0.53
    .).
    0.53
    .”
    0.52
    .}
    0.52
    。《
    0.50
    ).
    0.50
    .[
    0.50
    Activations Density 0.001%

    No Known Activations