© 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. 98185
    Prev
    Next
    INDEX
    Explanations

    Questions and user contexts

    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
     sachant
    -0.95
    -
    -0.94
    wot
    -0.92
     aix
    -0.92
    zoon
    -0.87
     osztály
    -0.86
    jy
    -0.86
     escudo
    -0.85
     Ер
    -0.84
     METH
    -0.84
    POSITIVE LOGITS
     derselbe
    1.08
    Atoi
    1.05
    想必
    1.04
    兩
    1.04
    囿
    1.04
    Ингредиенты
    1.01
    Ingredienti
    1.01
    Его
    0.98
    ција
    0.98
    Ман
    0.98
    Activations Density 0.000%

    No Known Activations