© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116202
    Prev
    Next
    INDEX
    Explanations

    turn out

    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
     turned
    -2.33
     turn
    -1.99
    turn
    -1.80
    turned
    -1.69
    Turn
    -1.68
     TURN
    -1.62
     Turned
    -1.58
     Turn
    -1.52
    Turned
    -1.47
    TURN
    -1.45
    POSITIVE LOGITS
     out
    2.34
     up
    0.93
     proving
    0.85
     allemaal
    0.77
     hervorragend
    0.75
     betekent
    0.73
     be
    0.72
     zaten
    0.71
    caixa
    0.70
    timetable
    0.70
    Activations Density 0.009%

    No Known Activations