© 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. 31-GEMMASCOPE-2-RES-262K
    7. 84766
    Prev
    Next
    INDEX
    Explanations

    shard key, safety principles, data strategy

    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
    ٪
    0.50
    セール
    0.48
    êmica
    0.46
    İM
    0.46
     autoplay
    0.44
    وامی
    0.44
     ವಿರು
    0.43
    یاء
    0.43
    ЕН
    0.43
     आफ्टरनून
    0.42
    POSITIVE LOGITS
    c
    0.51
     (
    0.45
     Center
    0.43
     be
    0.42
     d
    0.41
     For
    0.40
     ভবিষ্যতের
    0.40
     adapt
    0.39
     المركز
    0.39
     Lan
    0.39
    Activations Density 0.008%

    No Known Activations