© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67448
    Prev
    Next
    INDEX
    Explanations

    digitalcommons links

    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
     but
    -1.19
    yel
    -1.06
     But
    -1.05
     غذایی
    -1.04
     aikana
    -1.02
    celona
    -0.99
    vege
    -0.96
    abah
    -0.96
     restaurar
    -0.95
    娆
    -0.94
    POSITIVE LOGITS
    unción
    1.39
     QtCore
    1.30
    secta
    1.13
     услуги
    1.05
    iniques
    1.03
     सत्यापित
    1.02
    hamed
    1.02
    ouage
    1.02
    lında
    1.02
     סס
    1.01
    Activations Density 0.017%

    No Known Activations