© 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. 10-GEMMASCOPE-RES-131K
    7. 69051
    Prev
    Next
    INDEX
    Explanations

    events at locations

    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_10/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
     Voiture
    -1.17
    搋
    -1.17
     nouveautés
    -1.13
    ïc
    -1.13
    ssing
    -1.11
    tous
    -1.10
     verdadera
    -1.08
    odyear
    -1.05
    WEET
    -1.05
    ПИ
    -1.03
    POSITIVE LOGITS
     our
    1.47
     from
    1.42
    ְּ
    1.34
     three
    1.30
     by
    1.30
     этими
    1.29
     horribly
    1.27
     a
    1.24
     heightened
    1.24
     longtime
    1.23
    Activations Density 0.099%

    No Known Activations