© 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. 210387
    Prev
    Next
    INDEX
    Explanations

    API endpoints for resources

    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
     ንጥረ
    0.39
     women
    0.37
    downloader
    0.37
     レディース
    0.36
    Timestamp
    0.36
     ሂ
    0.36
    Women
    0.36
     pë
    0.36
     pixels
    0.36
    뛸
    0.36
    POSITIVE LOGITS
     bzw
    0.47
    ervices
    0.42
    忌
    0.41
    pecial
    0.40
    㐌
    0.40
    aderas
    0.39
    ttps
    0.39
    INEN
    0.38
    ชน์
    0.38
     previo
    0.38
    Activations Density 0.002%

    No Known Activations