© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 3875
    Prev
    Next
    INDEX
    Explanations

    graph nodes or array elements

    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
    :
    0.81
     inbox
    0.73
     tenders
    0.66
     Inbox
    0.66
    .
    0.64
    yfikacji
    0.63
     provide
    0.61
    。
    0.61
    ?
    0.60
     extravaganza
    0.59
    POSITIVE LOGITS
     важ
    0.64
     cualidades
    0.63
     важли
    0.60
    value
    0.59
     simbol
    0.59
     lezione
    0.59
     učen
    0.58
     MDLVertex
    0.57
     Beziehung
    0.57
    egraphics
    0.57
    Activations Density 1.078%

    No Known Activations