© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 12401
    Prev
    Next
    INDEX
    Explanations

    asking for input

    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_31_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
    觕
    0.55
    ก่อน
    0.50
    ebut
    0.50
    ärke
    0.48
    लीटर
    0.46
    迨
    0.46
    แบ่ง
    0.45
     მათი
    0.45
    秵
    0.45
     сложных
    0.45
    POSITIVE LOGITS
     has
    0.41
     document
    0.41
     the
    0.40
     have
    0.40
     intermediate
    0.40
     type
    0.39
    гам
    0.39
     representative
    0.38
     HP
    0.38
     one
    0.38
    Activations Density 0.020%

    No Known Activations