© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 17505
    Prev
    Next
    INDEX
    Explanations

    object coordinates and identifiers

    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
    "]["
    0.50
    是将
    0.40
     编辑
    0.38
    :“
    0.38
    编辑器
    0.37
     Editor
    0.37
     Transforms
    0.37
    :「
    0.36
    镶
    0.36
     mening
    0.36
    POSITIVE LOGITS
    HashCode
    0.40
    fileID
    0.40
    وی
    0.39
    Mur
    0.39
    جواب
    0.39
    𝓪
    0.38
     sewer
    0.37
    𝓬
    0.37
    Arkansas
    0.37
    jangan
    0.37
    Activations Density 0.000%

    No Known Activations