© 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-262K
    7. 71382
    Prev
    Next
    INDEX
    Explanations

    domain names and descriptions

    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_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
    l
    0.66
    i
    0.57
    s
    0.55
    y
    0.55
    t
    0.55
    x
    0.55
    n
    0.51
    users
    0.48
    k
    0.48
    w
    0.45
    POSITIVE LOGITS
     disseminating
    0.52
     খাজ
    0.52
     deliberations
    0.50
     dissemination
    0.48
     Understanding
    0.48
     प्रीम
    0.46
     أنّ
    0.46
     défis
    0.45
    ಂದರೆ
    0.45
    slideDuplicate
    0.45
    Activations Density 0.002%

    No Known Activations