© 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. 133696
    Prev
    Next
    INDEX
    Explanations

    for every

    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
     મારી
    0.38
    Organ
    0.37
     Smell
    0.36
    elementProp
    0.35
     ዘዴ
    0.35
     கற்ப
    0.35
    ">=</
    0.34
     যেমন
    0.34
     neurons
    0.34
     Bxa
    0.34
    POSITIVE LOGITS
     hochwertige
    0.40
    䤚
    0.40
     संके
    0.40
    াহিয়ার
    0.40
     پیشنه
    0.40
     पंचायतों
    0.39
     isc
    0.39
     Mafia
    0.39
     subterr
    0.39
    jaar
    0.39
    Activations Density 0.000%

    No Known Activations