© 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. 4002
    Prev
    Next
    INDEX
    Explanations

    late 2023/early 2024

    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
     Κ
    0.25
    (
    0.24
     Ν
    0.24
     ज्यात
    0.24
     Хер
    0.23
     in
    0.22
     Committee
    0.22
    ITT
    0.21
    นี้
    0.21
     name
    0.21
    POSITIVE LOGITS
    ين
    0.33
    ان
    0.31
    an
    0.31
    ü
    0.31
    activité
    0.31
    abilité
    0.30
    anfaatkan
    0.30
    v
    0.30
    f
    0.29
    า
    0.29
    Activations Density 0.130%

    No Known Activations