© 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. 36390
    Prev
    Next
    INDEX
    Explanations

    if you say dry

    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
     участи
    0.49
    ヤモンド
    0.47
    новой
    0.47
    튬
    0.47
    десят
    0.46
    стива
    0.46
     ука
    0.46
    itabbo
    0.46
     τραγ
    0.45
     angustato
    0.45
    POSITIVE LOGITS
    /
    0.63
    m
    0.50
     projects
    0.49
    (
    0.46
    mp
    0.44
     Govt
    0.44
     cock
    0.44
    Architect
    0.43
    lands
    0.43
    Features
    0.43
    Activations Density 0.007%

    No Known Activations