© 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. 285
    Prev
    Next
    INDEX
    Explanations

    photo attributions and sources

    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
     J
    -1.10
     B
    -1.07
     Â
    -1.05
     G
    -1.02
     Pe
    -1.02
     S
    -0.99
     C
    -0.97
     L
    -0.94
     H
    -0.93
     To
    -0.93
    POSITIVE LOGITS
     soportes
    1.15
     kleuren
    1.08
     tamaños
    1.04
    したが
    1.04
    ってもら
    1.03
     dámské
    1.00
     volledig
    0.99
     pomá
    0.97
     funguje
    0.97
     auttaa
    0.96
    Activations Density 0.128%

    No Known Activations