© 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. 191026
    Prev
    Next
    INDEX
    Explanations

    occasional sentence completions

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

    damage, face, shapes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    旣
    0.45
     нар
    0.44
    ずる
    0.41
     lái
    0.39
     hesitation
    0.39
     хоть
    0.39
     fibers
    0.39
    이기
    0.39
    催
    0.39
    投資
    0.38
    POSITIVE LOGITS
    kernels
    0.54
    ņi
    0.54
    atilde
    0.53
    ecc
    0.52
    s
    0.52
    remember
    0.50
    ilizar
    0.48
     economia
    0.48
    upper
    0.47
    notepad
    0.47
    Activations Density 0.000%

    No Known Activations