© 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. 49207
    Prev
    Next
    INDEX
    Explanations

    Objects, bundle, unusual activity

    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
    ז
    0.56
     jährlich
    0.50
     einer
    0.50
     rechts
    0.48
     autor
    0.47
     לש
    0.47
     fluctuations
    0.46
     excretion
    0.46
    Z
    0.46
     exorbit
    0.46
    POSITIVE LOGITS
    viewport
    0.55
    sockfd
    0.49
     नं
    0.49
    탄소년
    0.48
    Viewport
    0.46
     نتیجے
    0.45
    findViewById
    0.44
    esperienza
    0.43
    DependentUpon
    0.42
    রিদ
    0.42
    Activations Density 0.013%

    No Known Activations