© 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. 130428
    Prev
    Next
    INDEX
    Explanations

    certain following words

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

    information and reports

    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
    形成
    0.46
    舟
    0.44
     左
    0.43
     Drawn
    0.43
     becomes
    0.43
    க்கூட
    0.43
     tiene
    0.42
     maids
    0.42
     trapezium
    0.42
     一
    0.42
    POSITIVE LOGITS
    ຈັດສົ່ງ
    0.49
     franchises
    0.47
    ’
    0.46
    성
    0.46
    uillez
    0.45
     समितियों
    0.44
    মুর
    0.44
    נ
    0.44
    aco
    0.44
    ΤΟ
    0.43
    Activations Density 0.000%

    No Known Activations