© 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. 60830
    Prev
    Next
    INDEX
    Explanations

    final movement

    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
    ifc
    -0.91
    QUANTITY
    -0.84
     desean
    -0.81
     dissonance
    -0.80
    erring
    -0.78
     adder
    -0.77
    lesen
    -0.77
    größern
    -0.75
     Yahya
    -0.75
    while
    -0.75
    POSITIVE LOGITS
     movements
    2.75
     movement
    2.67
    movement
    2.19
     Movements
    2.06
    movements
    2.05
    Movement
    2.02
     Movement
    1.95
     movimiento
    1.75
     movimento
    1.60
     MOVEMENT
    1.60
    Activations Density 0.026%

    No Known Activations