© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117679
    Prev
    Next
    INDEX
    Explanations

    activity indicator

    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
    厲
    -0.83
    
    -0.78
     Ди
    -0.75
     ప
    -0.75
    IModel
    -0.74
     ultrasound
    -0.74
    Παραπομπές
    -0.73
    щем
    -0.73
     sir
    -0.73
     seguridad
    -0.73
    POSITIVE LOGITS
     activity
    1.26
    activity
    1.20
     INDIC
    1.10
     indicator
    1.05
    indicators
    1.02
    Indicator
    1.00
     Activity
    0.99
     ACTIVITY
    0.98
    indicator
    0.98
    indication
    0.95
    Activations Density 0.007%

    No Known Activations