© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 20991
    Prev
    Next
    INDEX
    Explanations

    text following punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    as
    1.30
    و
    1.19
    ع
    1.09
    al
    1.07
    ين
    1.07
    ма
    1.04
    ной
    1.04
    я
    1.03
    ة
    1.02
    ра
    1.01
    POSITIVE LOGITS
     (
    1.19
     for
    1.02
     ().
    0.86
     at
    0.86
    (
    0.85
    IK
    0.75
     scap
    0.73
    M
    0.70
    liness
    0.69
     chronology
    0.68
    Activations Density 0.121%

    No Known Activations