Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 12067
    Prev
    Next
    INDEX
    Explanations

    Exhibitors, ponds, pixels, world, UV, emissions, God

    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
     کوتا
    0.47
     Jap
    0.46
     toner
    0.46
     ಹ
    0.46
    новый
    0.46
     ಸೋ
    0.45
     FIGURE
    0.45
     கட்டடக்கலை
    0.45
     ಉತ್ತಮ
    0.45
     контро
    0.44
    POSITIVE LOGITS
    :
    0.43
    pentine
    0.42
    ر
    0.41
     Taxi
    0.41
    lger
    0.40
    Taxi
    0.40
     zak
    0.39
    rän
    0.39
    زاء
    0.39
    pmatrix
    0.39
    Activations Density 0.001%

    No Known Activations