© 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. 40-GEMMASCOPE-2-RES-262K
    7. 31271
    Prev
    Next
    INDEX
    Explanations

    numeric identifiers

    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_40_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
    igenous
    0.37
     overtaking
    0.36
    icultural
    0.35
    軒
    0.34
     kel
    0.33
     calibrate
    0.33
    දහ
    0.33
    ₁
    0.33
     recollect
    0.32
    <0xF0>
    0.32
    POSITIVE LOGITS
     숫자
    0.78
    数字
    0.69
     numeric
    0.66
    数値
    0.66
     numerical
    0.63
    numeric
    0.63
    數字
    0.63
    Numbers
    0.62
    numbers
    0.61
     숫
    0.61
    Activations Density 0.018%

    No Known Activations