© 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. 111199
    Prev
    Next
    INDEX
    Explanations

    historical context

    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
    盜
    0.41
    atsioon
    0.40
    挞
    0.40
     overrun
    0.40
     probleem
    0.39
    explos
    0.39
     சிங்கள
    0.39
    瓣
    0.39
    engono
    0.38
    დას
    0.38
    POSITIVE LOGITS
     ATP
    0.38
     DNA
    0.38
     Attractive
    0.38
     och
    0.37
     साँ
    0.36
     ড্রাই
    0.36
     Arap
    0.36
    Ꭿ
    0.36
     जी
    0.36
    issie
    0.35
    Activations Density 0.002%

    No Known Activations