© 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. 138822
    Prev
    Next
    INDEX
    Explanations

    languages, managing, maximum

    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
     свето
    0.58
     całkow
    0.58
    <unused1810>
    0.57
     нескольких
    0.56
     транспорти
    0.56
     〢
    0.54
     чувстви
    0.54
    䔋
    0.54
     미술
    0.54
     вікісторінку
    0.53
    POSITIVE LOGITS
    card
    0.56
     roles
    0.49
     let
    0.46
     pursuits
    0.46
    node
    0.46
     expanding
    0.45
    mb
    0.45
     v
    0.45
    men
    0.45
     populations
    0.44
    Activations Density 0.000%

    No Known Activations