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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 3302
    Prev
    Next
    INDEX
    Explanations

    identifying types of structured information

    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_65k_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
    ประจำ
    0.31
    ப்பிரிக்க
    0.30
    மான
    0.30
    paces
    0.30
    唑
    0.29
    moder
    0.28
    すす
    0.28
    acité
    0.27
    شو
    0.27
    ท
    0.27
    POSITIVE LOGITS
     itself
    0.44
    本身
    0.36
    片段
    0.35
     establishes
    0.31
     determines
    0.31
     opener
    0.30
     snippet
    0.29
     edges
    0.28
     определяет
    0.28
    γγελ
    0.28
    Activations Density 0.308%

    No Known Activations