© 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. 98595
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
     THEIR
    -1.01
     week
    -1.00
     регионе
    -0.98
    their
    -0.97
    راً
    -0.94
     Friday
    -0.94
     Thursday
    -0.93
    week
    -0.91
     miércoles
    -0.91
    communications
    -0.90
    POSITIVE LOGITS
     lager
    1.16
     лагер
    1.13
     seleccionadas
    1.11
    Ḥ
    1.03
    pañol
    1.02
    ريقيا
    1.02
    <blockquote>
    1.00
    raciones
    0.99
     motorway
    0.99
     escritas
    0.98
    Activations Density 0.168%

    No Known Activations