© 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. 133599
    Prev
    Next
    INDEX
    Explanations

    generate responses (refusals)

    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
    űkö
    0.40
    seems
    0.39
    privacy
    0.39
    めちゃ
    0.39
    Seems
    0.39
     zask
    0.38
    Ử
    0.37
    カフェ
    0.37
     学習
    0.37
    争
    0.37
    POSITIVE LOGITS
    ষ্ঠান
    0.44
     the
    0.44
     क्रा
    0.44
     community
    0.43
     Mon
    0.43
     Dungeon
    0.42
     beans
    0.42
    ville
    0.42
     Town
    0.41
     crafts
    0.41
    Activations Density 0.003%

    No Known Activations