© 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. 187342
    Prev
    Next
    INDEX
    Explanations

    bigger the LCD

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

    grappling with difficult things

    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
    vari
    0.49
     congregate
    0.49
    il
    0.48
     ',
    0.47
     employ
    0.47
     vari
    0.47
    Vari
    0.46
    r
    0.46
     standardize
    0.45
    ad
    0.44
    POSITIVE LOGITS
    нення
    0.48
     خلال
    0.48
    ソッド
    0.48
     έως
    0.47
     comprimento
    0.46
     தொடங்கியது
    0.46
     ਫ
    0.46
     Skywalker
    0.46
    οδο
    0.45
     ล้าน
    0.45
    Activations Density 0.001%

    No Known Activations