© 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. 86675
    Prev
    Next
    INDEX
    Explanations

    scavenger or treasure hunts

    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
    V
    0.64
    मल
    0.64
    i
    0.64
    K
    0.61
    :
    0.60
    is
    0.59
    a
    0.57
    S
    0.57
    ളെ
    0.56
    afe
    0.55
    POSITIVE LOGITS
     එය
    0.63
    но
    0.55
    он
    0.55
     учре
    0.55
     уровнем
    0.55
     և
    0.54
     М
    0.54
     ожида
    0.53
    ancis
    0.53
     পড়বে
    0.52
    Activations Density 0.001%

    No Known Activations