© 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-65K
    7. 3937
    Prev
    Next
    INDEX
    Explanations

    actions that go beyond

    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_65k_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
    宻
    0.38
    ユニ
    0.38
    カイ
    0.36
     restrooms
    0.36
    ിൽ
    0.35
     whatnot
    0.35
    িল্প
    0.35
     ഇ
    0.34
    ሎች
    0.34
     ユニ
    0.34
    POSITIVE LOGITS
    ran
    0.49
    q
    0.41
    с
    0.41
     pleaded
    0.40
     took
    0.39
     responded
    0.39
     بسیاری
    0.39
    罕
    0.38
     hesitated
    0.38
     invariable
    0.38
    Activations Density 0.037%

    No Known Activations