© 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. 31-GEMMASCOPE-2-RES-65K
    4. 11007
    Prev
    Next
    INDEX
    Explanations

    numerical comparison <=

    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
     excellent
    0.43
     upper
    0.39
    (
    0.39
     semi
    0.38
     autistic
    0.37
     "
    0.37
    ️
    0.37
    isser
    0.36
     accessible
    0.36
     apartment
    0.36
    POSITIVE LOGITS
     или
    0.50
     这些
    0.47
     বা
    0.46
     развития
    0.45
    haran
    0.45
     нулю
    0.44
     Маке
    0.44
     нашей
    0.44
     ».
    0.43
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.43
    Activations Density 0.017%

    No Known Activations