© 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. 418
    Prev
    Next
    INDEX
    Explanations

    icon and font usage

    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
     높
    -0.81
    Те
    -0.74
     ADR
    -0.72
     redirection
    -0.71
     airsoft
    -0.71
    為什麼
    -0.70
    Για
    -0.70
    Jules
    -0.69
     sélection
    -0.69
    Scotland
    -0.68
    POSITIVE LOGITS
     icons
    1.73
     Icon
    1.59
     icon
    1.58
    icons
    1.56
     Icons
    1.54
    font
    1.51
     font
    1.48
     Font
    1.47
    Icons
    1.46
    icon
    1.43
    Activations Density 0.050%

    No Known Activations