© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 493
    Prev
    Next
    INDEX
    Explanations

    reversals, dinner, intricate, fulfill

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    puts
    1.41
     provides
    1.32
    他对
    1.28
     gave
    1.27
     under
    1.27
     traz
    1.27
    】-
    1.25
    dert
    1.25
     Dort
    1.22
     brings
    1.21
    POSITIVE LOGITS
     추출
    1.03
     shinobi
    0.99
     Circulation
    0.98
    lafen
    0.94
     Grayson
    0.91
     CFS
    0.91
     BatchNorm
    0.89
    남
    0.89
     Fractal
    0.88
    cfe
    0.86
    Activations Density 0.031%

    No Known Activations