© 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. 18091
    Prev
    Next
    INDEX
    Explanations

    figure and caption formatting

    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
    chanted
    0.50
    UserNotification
    0.46
    ݢ
    0.42
    îne
    0.40
    ريبات
    0.40
    Gravestone
    0.40
    initiative
    0.39
     iniciativas
    0.39
    ਸ
    0.39
     iniciativa
    0.39
    POSITIVE LOGITS
    minipage
    0.71
    subfigure
    0.71
    subfloat
    0.70
     sub
    0.63
     caption
    0.58
     captions
    0.55
    hspace
    0.52
     horizontally
    0.50
     subplot
    0.49
     spacer
    0.47
    Activations Density 0.003%

    No Known Activations