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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 31951
    Prev
    Next
    INDEX
    Explanations

    canny, scan, install, fault

    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
     equivalent
    0.38
     typical
    0.37
    ,.
    0.37
     typically
    0.36
     típ
    0.36
     ó
    0.36
     immovable
    0.36
     recently
    0.35
     چرا
    0.35
     mostr
    0.35
    POSITIVE LOGITS
    ەن
    0.41
     πάν
    0.41
    𝑯
    0.39
    াগর
    0.39
     quét
    0.39
     هەر
    0.38
     గారి
    0.38
    魧
    0.38
    вак
    0.37
     دیے
    0.36
    Activations Density 0.030%

    No Known Activations