© 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. 16-GEMMASCOPE-2-RES-262K
    7. 9125
    Prev
    Next
    INDEX
    Explanations

    categories and concepts

    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
    ol
    1.56
    A
    1.48
    ing
    1.47
    G
    1.46
    T
    1.38
    R
    1.38
    the
    1.37
    ac
    1.34
    ine
    1.32
    M
    1.31
    POSITIVE LOGITS
    يل
    1.13
     peligro
    1.02
     rougeâtres
    0.99
     但是
    0.98
     propias
    0.97
     kayaks
    0.97
    เป็น
    0.96
    كين
    0.96
     विभागों
    0.95
     сервис
    0.95
    Activations Density 0.211%

    No Known Activations