© 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. 9022
    Prev
    Next
    INDEX
    Explanations

    AI Assistants

    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
    6
    0.64
    -
    0.63
    8
    0.63
    9
    0.59
     durante
    0.58
     (
    0.56
    4
    0.55
     Archivado
    0.54
     kvůli
    0.54
    }.}
    0.53
    POSITIVE LOGITS
     건물
    0.59
     QuantityOnHand
    0.56
     bangunan
    0.54
     earthen
    0.53
     istnie
    0.52
     bâtiments
    0.52
     ಉತ್ಪ
    0.52
     buildings
    0.51
    buildings
    0.51
     demás
    0.50
    Activations Density 1.908%

    No Known Activations