© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144322
    Prev
    Next
    INDEX
    Explanations

    led astray

    np_acts-logits-general · gemini-2.5-flash-lite

    "You" or "This"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ül
    0.48
    ਮ
    0.46
    蠱
    0.44
    竈
    0.43
    Efter
    0.43
     incubation
    0.43
    ’
    0.43
    Neurons
    0.42
    噉
    0.42
    利益
    0.42
    POSITIVE LOGITS
     squarely
    0.54
     splashed
    0.49
     dioc
    0.47
     veja
    0.46
    nThe
    0.46
     conspicuously
    0.46
     does
    0.44
     dosy
    0.44
     dehors
    0.44
    caya
    0.43
    Activations Density 0.000%

    No Known Activations