© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16362
    Prev
    Next
    INDEX
    Explanations

    year

    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
     that
    -1.02
     what
    -1.00
     surfactants
    -0.98
     +
    -0.95
     sano
    -0.91
    ارب
    -0.91
     نظر
    -0.89
     patata
    -0.88
    Philippine
    -0.87
    SARAH
    -0.87
    POSITIVE LOGITS
     večer
    1.37
     nemoc
    1.14
     yesterday
    1.12
    褻
    1.12
    Mr
    1.12
     będę
    1.06
     embalaje
    1.05
     বল
    1.05
     vč
    1.04
     portátiles
    1.04
    Activations Density 0.001%

    No Known Activations