© 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. 6480
    Prev
    Next
    INDEX
    Explanations

    people's qualities or roles

    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
    ÇÃO
    0.39
    दिल्ली
    0.38
     выполняется
    0.38
    醜
    0.38
     blanditiis
    0.37
     الشعر
    0.36
    URATION
    0.35
     coś
    0.35
     ユ
    0.35
     галу
    0.35
    POSITIVE LOGITS
     thinker
    0.91
     performer
    0.91
     thinkers
    0.85
     person
    0.83
     communicator
    0.80
    之人
    0.78
     player
    0.77
     guy
    0.77
     performers
    0.76
     човек
    0.75
    Activations Density 0.023%

    No Known Activations