© 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. 13921
    Prev
    Next
    INDEX
    Explanations

    coordinates and random generation

    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
     Wants
    0.44
     ['
    0.41
     Rectangle
    0.41
     Carlson
    0.39
     [
    0.39
     rectangle
    0.38
     Purchase
    0.38
     Horse
    0.38
     Elizabeth
    0.38
     contemplating
    0.38
    POSITIVE LOGITS
     продукт
    0.46
    ছার
    0.46
     toug
    0.45
    ֡
    0.45
    Ꮷ
    0.44
     സൃഷ്ട
    0.43
    Inn
    0.43
    KURZ
    0.43
    testAvg
    0.42
    SOL
    0.42
    Activations Density 0.002%

    No Known Activations