© 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. 6543
    Prev
    Next
    INDEX
    Explanations

    code loop structure

    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
     capitalize
    0.41
    ρεύ
    0.39
    નુ
    0.36
    ስቃሴ
    0.36
    팻
    0.36
    ผน
    0.36
     toning
    0.36
     aquifers
    0.36
     capitalizing
    0.36
     ironic
    0.35
    POSITIVE LOGITS
     Kame
    0.38
     Ю
    0.36
     துணை
    0.34
    控件
    0.33
     Wikimedia
    0.33
    Turtle
    0.33
    sor
    0.33
    OB
    0.33
    estr
    0.33
    ፓ
    0.33
    Activations Density 0.002%

    No Known Activations