© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77942
    Prev
    Next
    INDEX
    Explanations

    code formatting and beautifying

    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
    ITION
    -0.85
    ixels
    -0.79
    ENSION
    -0.76
    gust
    -0.75
    ︵
    -0.74
    caption
    -0.73
     powied
    -0.73
     ukry
    -0.72
    フィック
    -0.71
    ixel
    -0.71
    POSITIVE LOGITS
     indent
    1.99
    indent
    1.77
    Indent
    1.71
     beau
    1.66
     indentation
    1.58
     Ind
    1.55
    beau
    1.55
     indented
    1.50
    pretty
    1.48
     pretty
    1.46
    Activations Density 0.056%

    No Known Activations