© 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. 80968
    Prev
    Next
    INDEX
    Explanations

    grant, granted, security permissions

    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
    swig
    -0.75
     tę
    -0.73
     vorgesch
    -0.71
    Ū
    -0.71
    Պ
    -0.70
     arrows
    -0.69
    ChildScrollView
    -0.69
     clapping
    -0.68
    Routes
    -0.68
     historique
    -0.67
    POSITIVE LOGITS
     granted
    0.92
    granted
    0.85
     UIP
    0.84
     parking
    0.82
    ねえ
    0.78
     grant
    0.77
    grant
    0.77
    undra
    0.77
    bob
    0.75
    高さ
    0.75
    Activations Density 0.082%

    No Known Activations