© 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. 17920
    Prev
    Next
    INDEX
    Explanations

    text wrapping options like tk.WORD

    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
    摘要
    0.41
    Favorites
    0.41
    SH
    0.38
    Memory
    0.38
     template
    0.38
    ジ
    0.38
    াবা
    0.37
    दिष्ट
    0.37
     eaves
    0.36
     шабло
    0.36
    POSITIVE LOGITS
     Editors
    0.45
     Controlled
    0.43
    editors
    0.42
     Editor
    0.42
     Modena
    0.42
    ⓒ
    0.41
     Editing
    0.40
     editors
    0.40
    Controlled
    0.40
     Spec
    0.40
    Activations Density 0.002%

    No Known Activations