© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 36674
    Prev
    Next
    INDEX
    Explanations

    classes, work shifts, etc

    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
    נו
    0.50
    t
    0.49
    Dire
    0.47
    Casey
    0.47
     Caspian
    0.47
    Liga
    0.46
    ט
    0.46
     Asoci
    0.46
    ت
    0.46
    дру
    0.46
    POSITIVE LOGITS
     diplomas
    0.55
     attaining
    0.50
     dinners
    0.49
     devotes
    0.49
     sermons
    0.48
    ক্ষা
    0.47
     interrupts
    0.47
     stipulates
    0.46
     allClasses
    0.46
     fooling
    0.46
    Activations Density 0.006%

    No Known Activations