© 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. 29886
    Prev
    Next
    INDEX
    Explanations

    how and descriptive words

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

    shell commands with awk

    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
    平
    0.46
    븐
    0.45
    ciate
    0.43
     prefect
    0.43
     Pref
    0.42
     आयु
    0.41
     Mailing
    0.40
    COG
    0.40
    ጭ
    0.39
    ประ
    0.39
    POSITIVE LOGITS
     कमा
    0.50
     کھانے
    0.50
     مانند
    0.49
     successo
    0.47
     ciała
    0.47
     snacking
    0.46
     bottlene
    0.46
     нәрсә
    0.45
     casser
    0.43
     dinding
    0.43
    Activations Density 0.000%

    No Known Activations