© 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. 7868
    Prev
    Next
    INDEX
    Explanations

    python library imports

    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
    👃
    0.46
    াক
    0.44
     বাঙ্গাল
    0.44
    முகச்
    0.43
    鬍
    0.43
    াঙ্গ
    0.42
    鬣
    0.42
    橑
    0.42
    嵬
    0.41
    ަށް
    0.41
    POSITIVE LOGITS
     sys
    0.68
     os
    0.66
     Py
    0.62
     pyt
    0.61
     py
    0.60
     hashlib
    0.59
    py
    0.59
    sys
    0.59
    subprocess
    0.57
    openai
    0.57
    Activations Density 0.066%

    No Known Activations