© 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. 216186
    Prev
    Next
    INDEX
    Explanations

    put in quantity or addition

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

    comparison words

    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
    ز
    0.50
    W
    0.50
    Survey
    0.49
    Crisis
    0.49
    Ultimate
    0.48
    وا
    0.48
    J
    0.48
    崑
    0.47
    ف
    0.46
    Who
    0.46
    POSITIVE LOGITS
     alot
    0.52
     prog
    0.49
     bellow
    0.48
     nid
    0.46
     ineffective
    0.46
     pellet
    0.46
     mottled
    0.46
     mute
    0.46
     provoking
    0.46
     bateria
    0.45
    Activations Density 0.001%

    No Known Activations