© 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. 71015
    Prev
    Next
    INDEX
    Explanations

    #define

    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
    weetie
    -0.92
    mitsub
    -0.89
     Anhänger
    -0.88
    ARROLL
    -0.86
    他也
    -0.85
     same
    -0.85
    Prí
    -0.85
    mycompany
    -0.84
    Rück
    -0.84
    álna
    -0.84
    POSITIVE LOGITS
    กรณ์
    0.90
     retirar
    0.86
     zacht
    0.84
     상태
    0.83
    攒
    0.80
     Walkover
    0.79
     Raider
    0.79
    错过
    0.77
    ndata
    0.76
     Irlanda
    0.75
    Activations Density 0.005%

    No Known Activations