© 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. 8097
    Prev
    Next
    INDEX
    Explanations

    code construct following `(`

    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
    蹼
    0.32
    テナンス
    0.32
    🈚
    0.32
    壹百
    0.30
    ClearedBy
    0.30
    <unused266>
    0.30
    𒋼
    0.29
    🚻
    0.29
    🚱
    0.29
    স্বর
    0.29
    POSITIVE LOGITS
     using
    0.43
     `
    0.42
     use
    0.39
    <code>
    0.38
     ```
    0.36
     Simple
    0.35
     functions
    0.32
     usare
    0.32
     Using
    0.32
     *
    0.31
    Activations Density 0.147%

    No Known Activations