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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34669
    Prev
    Next
    INDEX
    Explanations

    stroke width

    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_34/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
    verez
    -0.83
    TokenNameDOT
    -0.83
    シップ
    -0.81
     маль
    -0.81
    +:+
    -0.80
    USF
    -0.76
    LARE
    -0.75
    AnchorTagHelper
    -0.75
     baños
    -0.75
    inquirer
    -0.75
    POSITIVE LOGITS
     width
    0.82
    utschein
    0.74
    お茶
    0.71
     souvenir
    0.71
    ürzt
    0.66
     ادامه
    0.65
    を変える
    0.65
    Width
    0.65
    قق
    0.65
    width
    0.64
    Activations Density 0.036%

    No Known Activations