© 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. 31-GEMMASCOPE-2-RES-262K
    7. 71941
    Prev
    Next
    INDEX
    Explanations

    links to explicit content or mod repositories

    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_31_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
    ith
    0.62
    mi
    0.50
    0
    0.49
    ax
    0.48
    8
    0.48
    ay
    0.47
    ud
    0.46
    Р
    0.46
    5
    0.46
    ar
    0.46
    POSITIVE LOGITS
     فائلوں
    0.48
     చాలా
    0.47
     buddhav
    0.47
    ukiyoe
    0.47
     imdb
    0.45
     ግራም
    0.45
     xếp
    0.45
    കളും
    0.44
     dhinak
    0.43
    ល្អ
    0.42
    Activations Density 0.004%

    No Known Activations