© 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. 6935
    Prev
    Next
    INDEX
    Explanations

    multilingual components

    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
     that
    1.53
     was
    1.51
    ่
    1.47
    ,
    1.39
    L
    1.39
     =
    1.38
     to
    1.35
    ์
    1.34
     it
    1.25
    ηση
    1.24
    POSITIVE LOGITS
    ла
    1.41
    k
    1.34
    ל
    1.33
    يد
    1.27
    ра
    1.17
    ün
    1.14
    يان
    1.12
    re
    1.11
    är
    1.11
    يه
    1.05
    Activations Density 0.150%

    No Known Activations