© 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. 132
    Prev
    Next
    INDEX
    Explanations

    programmıng structures and concepts

    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
     Pagina
    -0.94
     endwhile
    -0.91
     niitä
    -0.90
     expérimentés
    -0.89
     Soit
    -0.89
     avocat
    -0.89
     pittores
    -0.89
    殽
    -0.86
     réparation
    -0.85
     flé
    -0.85
    POSITIVE LOGITS
     without
    1.02
     any
    0.94
     on
    0.90
     or
    0.85
     holds
    0.84
     NZ
    0.81
     extending
    0.81
     ilustracji
    0.80
    ko
    0.79
     hold
    0.79
    Activations Density 0.040%

    No Known Activations