© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118103
    Prev
    Next
    INDEX
    Explanations

    took a turn

    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
    estroyer
    -0.98
    ambu
    -0.90
    őz
    -0.86
    usz
    -0.83
    fikasi
    -0.80
    靑
    -0.80
    lofen
    -0.78
     FLOAT
    -0.77
    uelos
    -0.75
    Perth
    -0.75
    POSITIVE LOGITS
     turn
    2.89
    turn
    2.16
     turns
    2.09
     Turn
    1.95
    Turn
    1.88
     twist
    1.85
     twists
    1.83
     TURN
    1.74
     took
    1.71
     turned
    1.68
    Activations Density 0.024%

    No Known Activations