© 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. 61178
    Prev
    Next
    INDEX
    Explanations

    Rupert, Vanessa, LogLevel, snprintf, AccessToken, plumber

    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
    o
    -3.23
    でも
    -3.03
    ной
    -2.52
    quot
    -2.50
     mais
    -2.45
    ia
    -2.44
    ie
    -2.44
    amp
    -2.42
    mathrm
    -2.39
     prioriti
    -2.36
    POSITIVE LOGITS
    !’
    2.38
    鱘
    2.31
    []
    2.30
     體
    2.22
    念头
    2.22
    してみる
    2.22
    berikut
    2.20
    鱺
    2.19
     klikken
    2.19
     allzu
    2.17
    Activations Density 0.010%

    No Known Activations