© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 6823
    Prev
    Next
    INDEX
    Explanations

    Ritz, Fitz, Spitz, Carlton

    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
    Ʈ
    -0.77
     getEmail
    -0.77
     getX
    -0.73
     Wachs
    -0.72
     IllegalArgument
    -0.71
     feind
    -0.71
     скло
    -0.71
    Ahol
    -0.70
     głównie
    -0.70
    provincia
    -0.69
    POSITIVE LOGITS
    Brush
    0.79
    fillRect
    0.75
    ộ
    0.73
     Carab
    0.70
     Carlton
    0.70
     Penta
    0.70
    lton
    0.69
    meln
    0.69
     זאת
    0.68
    zió
    0.68
    Activations Density 0.029%

    No Known Activations