© 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. 37828
    Prev
    Next
    INDEX
    Explanations

    scroll point

    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
     bl
    -0.66
    erape
    -0.64
    يكون
    -0.63
    Kura
    -0.62
    にな
    -0.61
    はこの
    -0.61
     คน
    -0.60
    ーラー
    -0.60
     Peter
    -0.59
     Vulcan
    -0.59
    POSITIVE LOGITS
     Brau
    0.77
     refinements
    0.75
     Marijuana
    0.75
    mutations
    0.75
    WEBPACK
    0.73
    wier
    0.73
    ppe
    0.72
    Speak
    0.71
    Restricted
    0.71
    ሌ
    0.71
    Activations Density 0.034%

    No Known Activations