© 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. 120359
    Prev
    Next
    INDEX
    Explanations

    making choices or commitments

    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
     इज
    0.43
    astere
    0.41
     フォ
    0.41
     olha
    0.40
    Yz
    0.40
    nicy
    0.38
    éch
    0.38
    
    0.38
     இருந்து
    0.37
    ასი
    0.37
    POSITIVE LOGITS
    grad
    0.38
     CPU
    0.37
     Moder
    0.37
    ved
    0.36
    ICAL
    0.36
     trop
    0.33
    cen
    0.33
     stallion
    0.33
     Trop
    0.33
     shipyard
    0.33
    Activations Density 0.000%

    No Known Activations