© 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. 133624
    Prev
    Next
    INDEX
    Explanations

    descriptive noun followed by a verb

    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
    記述
    0.40
    美好
    0.39
     curricula
    0.39
     Jiménez
    0.38
     immunos
    0.38
    🎆
    0.37
     sadde
    0.36
    जिब
    0.36
     upd
    0.36
    giving
    0.36
    POSITIVE LOGITS
     강
    0.38
    Pete
    0.36
    Songs
    0.35
    ﺔ
    0.35
    ypes
    0.34
     Offer
    0.34
     δυνα
    0.34
    hwnd
    0.34
     Publicity
    0.34
    强度
    0.34
    Activations Density 0.001%

    No Known Activations