© 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. 120198
    Prev
    Next
    INDEX
    Explanations

    "hail" exclamations

    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
    ible
    0.42
    害
    0.41
    这个人
    0.41
    背
    0.41
    able
    0.39
     গেলো
    0.39
     ins
    0.38
    ib
    0.38
    istic
    0.38
    iply
    0.38
    POSITIVE LOGITS
    (',',$
    0.47
     módulo
    0.45
    тись
    0.43
    সঙ্গ
    0.42
    তোমার
    0.41
    }_{[
    0.40
     pedir
    0.39
    тия
    0.39
     bilateral
    0.39
     kok
    0.39
    Activations Density 0.000%

    No Known Activations