© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40829
    Prev
    Next
    INDEX
    Explanations

    if else elseif catch contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     them
    -1.79
    羮
    -1.52
    カッコいい
    -1.45
     ソックス
    -1.38
    ⽼
    -1.36
    殽
    -1.35
    みたら
    -1.35
    开车
    -1.34
     elétrica
    -1.34
     rapidamente
    -1.33
    POSITIVE LOGITS
    there
    1.68
     зді
    1.57
     et
    1.55
     There
    1.55
     as
    1.53
     etc
    1.52
     усі
    1.47
     will
    1.44
     sierpnia
    1.41
    There
    1.36
    Activations Density 0.002%

    No Known Activations