© 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. 22-GEMMASCOPE-RES-131K
    7. 28190
    Prev
    Next
    INDEX
    Explanations

    advertisement or product description

    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_22/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
     diferencias
    -1.18
     któ
    -1.02
     estaciones
    -0.98
     ktoré
    -0.95
     múltip
    -0.94
     decenas
    -0.94
     generaciones
    -0.94
     limitaciones
    -0.94
    ets
    -0.94
    即便
    -0.93
    POSITIVE LOGITS
     with
    1.27
     jelasnya
    1.21
     vold
    1.16
     publice
    1.15
     Gratis
    1.14
     GRATIS
    1.13
     tirs
    1.13
     fuo
    1.13
     lampada
    1.13
    】:
    1.13
    Activations Density 0.072%

    No Known Activations