© 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. 30609
    Prev
    Next
    INDEX
    Explanations

    index of iterative operations

    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
     када
    0.45
     ['$
    0.41
     Palmas
    0.41
    孱
    0.38
    ->$
    0.38
    갸
    0.37
    مدة
    0.37
    اعات
    0.37
    駆
    0.36
    ute
    0.36
    POSITIVE LOGITS
    (&(
    0.41
    이라는
    0.36
    ^{-(
    0.36
     žel
    0.36
     दिखाता
    0.35
    Rock
    0.35
     राख
    0.34
     рок
    0.33
     হইলেন
    0.33
    žev
    0.33
    Activations Density 0.025%

    No Known Activations