© 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. 16-GEMMASCOPE-2-RES-262K
    7. 40729
    Prev
    Next
    INDEX
    Explanations

    original message or email subject

    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_16_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
    мо
    0.72
    ро
    0.70
    ла
    0.69
    场
    0.66
    ле
    0.65
    ون
    0.63
    мета
    0.62
    мара
    0.60
    مل
    0.59
    住宅
    0.59
    POSITIVE LOGITS
     by
    0.60
     l
    0.57
     क्योंकि
    0.57
    s
    0.57
     Alfredo
    0.56
    𒐪
    0.56
    o
    0.55
     to
    0.54
     sent
    0.54
     Beech
    0.53
    Activations Density 0.000%

    No Known Activations