© 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. 210529
    Prev
    Next
    INDEX
    Explanations

    head-to-head comparison

    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
     advantage
    0.44
    aried
    0.40
     jind
    0.39
    ilde
    0.39
    緯
    0.39
    ary
    0.38
     address
    0.38
    ulse
    0.38
    ter
    0.38
     accessory
    0.38
    POSITIVE LOGITS
    ㄅ
    0.43
    Бі
    0.39
    ٘
    0.37
     Оксана
    0.37
     Gameplay
    0.36
    眅
    0.36
    棿
    0.36
    smoke
    0.36
    نه
    0.36
    चणी
    0.36
    Activations Density 0.000%

    No Known Activations