© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69986
    Prev
    Next
    INDEX
    Explanations

    lists features and options

    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_10/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
     with
    -2.89
     because
    -2.36
     through
    -2.31
     during
    -2.30
     one
    -2.25
     without
    -2.13
     from
    -2.05
     when
    -2.02
     in
    -2.00
     situations
    -1.98
    POSITIVE LOGITS
     serre
    2.17
     gouttes
    1.98
     juger
    1.97
     corriger
    1.96
     faciliter
    1.96
     vanille
    1.94
     fermer
    1.94
    毟
    1.92
     Eſ
    1.89
    
    1.85
    Activations Density 0.215%

    No Known Activations