© 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. 65993
    Prev
    Next
    INDEX
    Explanations

    about to

    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
     genoux
    -2.13
     rayures
    -1.95
     tromper
    -1.88
    龗
    -1.78
     compromisos
    -1.73
     vôtre
    -1.70
    every
    -1.69
     familières
    -1.68
     relâche
    -1.66
     bidra
    -1.66
    POSITIVE LOGITS
     to
    2.75
     Because
    1.93
     It
    1.84
     
    1.83
     Both
    1.82
     Another
    1.80
     used
    1.71
     be
    1.68
     have
    1.66
     Sadly
    1.66
    Activations Density 0.006%

    No Known Activations