© 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. 6055
    Prev
    Next
    INDEX
    Explanations

    apps rely / actively preserved

    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
     この
    0.44
    ‖</
    0.43
     }{}_{\
    0.42
     または
    0.39
    這一
    0.39
     jumbo
    0.38
     covering
    0.37
     ((*
    0.37
     TNumber
    0.37
    alary
    0.37
    POSITIVE LOGITS
     Interface
    0.40
     Everyone
    0.38
     ihm
    0.38
     دانشج
    0.38
     People
    0.38
    vm
    0.38
    untu
    0.37
     Everybody
    0.37
    System
    0.37
     Signing
    0.37
    Activations Density 0.008%

    No Known Activations