© 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. 31-GEMMASCOPE-2-RES-262K
    7. 1458
    Prev
    Next
    INDEX
    Explanations

    academic departments and fields

    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
     captcha
    0.29
    嬸
    0.27
     feme
    0.27
     ignorance
    0.27
     poetry
    0.27
     treason
    0.27
    MeToo
    0.27
     monog
    0.26
     girly
    0.26
     standar
    0.26
    POSITIVE LOGITS
    与
    0.29
     и
    0.28
    *\
    0.27
     化
    0.27
    と
    0.27
    Optimization
    0.27
     এবং
    0.26
     and
    0.26
     और
    0.26
     和
    0.26
    Activations Density 0.009%

    No Known Activations