© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 6294
    Prev
    Next
    INDEX
    Explanations

    program entry point declarations

    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
    ース
    0.35
    эт
    0.33
    掲
    0.33
    <th>
    0.33
     λειτουργ
    0.33
     "@{
    0.33
    VING
    0.32
     اخرى
    0.32
    槻
    0.31
    ('@
    0.31
    POSITIVE LOGITS
    권을
    0.36
     rechten
    0.35
    spac
    0.35
     rights
    0.35
     defaultConfig
    0.35
     Rights
    0.33
     declaration
    0.33
     quyền
    0.32
    權
    0.32
     권
    0.32
    Activations Density 0.000%

    No Known Activations