Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 14725
    Prev
    Next
    INDEX
    Explanations

    invitations and events

    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
    놈
    0.50
     booze
    0.49
    🤯
    0.47
     однозна
    0.45
    🤬
    0.45
     俺
    0.45
     অবিশ্বাস্য
    0.43
     brewery
    0.43
     💪
    0.43
     overkill
    0.42
    POSITIVE LOGITS
     hostess
    0.80
    lovely
    0.58
     lovely
    0.57
     luncheon
    0.56
     guests
    0.55
     Guests
    0.55
     ospiti
    0.54
    Guests
    0.54
     Host
    0.54
     मेजब
    0.53
    Activations Density 0.002%

    No Known Activations