© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 5985
    Prev
    Next
    INDEX
    Explanations

    question answers or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     nightmare
    0.79
     всеми
    0.76
     Wonder
    0.75
    बंध
    0.74
    끔
    0.74
    تين
    0.73
    MOB
    0.73
    FILE
    0.73
     l
    0.72
    MAX
    0.72
    POSITIVE LOGITS
     dingin
    0.78
     objectifs
    0.76
     گویا
    0.75
    及其
    0.75
    ත්මක
    0.74
    ertools
    0.74
    نىڭ
    0.73
     Objectives
    0.72
    find
    0.71
    hores
    0.70
    Activations Density 0.000%

    No Known Activations