© 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. 40-GEMMASCOPE-2-RES-262K
    7. 7945
    Prev
    Next
    INDEX
    Explanations

    numerical ranges and costs

    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_40_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
    Stabilise
    0.22
    镛
    0.22
    RawO
    0.21
    怿
    0.21
     אטאטורק
    0.21
    ıyoruz
    0.21
     Đế
    0.20
    蒎
    0.20
     ذریع
    0.20
    𐰀
    0.20
    POSITIVE LOGITS
     nine
    0.32
     five
    0.32
     eight
    0.32
     seven
    0.29
    0.28
     three
    0.28
     six
    0.27
     twenty
    0.26
     ten
    0.26
     four
    0.26
    Activations Density 0.144%

    No Known Activations