© 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. 60031
    Prev
    Next
    INDEX
    Explanations

    Buffer, born, other, Q

    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
    lien
    -0.82
     at
    -0.80
    skog
    -0.79
    ึง
    -0.77
     casinos
    -0.76
    øver
    -0.76
    travel
    -0.75
    Ox
    -0.75
    enzo
    -0.75
     not
    -0.74
    POSITIVE LOGITS
    ungkapkan
    0.80
     Problemen
    0.78
     hyaluronic
    0.77
    INCLUDES
    0.75
    therape
    0.75
    BeginInit
    0.75
    )>=
    0.75
    が含ま
    0.74
     ארו
    0.74
    quial
    0.73
    Activations Density 0.001%

    No Known Activations