© 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. 110845
    Prev
    Next
    INDEX
    Explanations

    specific words and following tokens

    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
    譲
    0.43
     dhammo
    0.43
     inheriting
    0.43
     directing
    0.41
    setBadge
    0.40
    instag
    0.39
     collision
    0.38
    scriber
    0.38
    上げて
    0.38
    initiated
    0.38
    POSITIVE LOGITS
    远离
    0.45
    防控
    0.39
     ১৩
    0.38
     профилакти
    0.36
     وقلنا
    0.36
    +}\
    0.36
     [.
    0.35
     Footer
    0.34
     Algun
    0.34
    ([
    0.33
    Activations Density 0.001%

    No Known Activations