© 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. 34-GEMMASCOPE-RES-131K
    7. 56065
    Prev
    Next
    INDEX
    Explanations

    version 3 of the License

    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_34/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
    JTextField
    -0.77
    sacrifice
    -0.74
    楨
    -0.71
    println
    -0.70
     Hodgson
    -0.69
    ック
    -0.69
    ным
    -0.68
    Circle
    -0.68
    Cs
    -0.67
    Création
    -0.67
    POSITIVE LOGITS
    MessageType
    0.67
    を示
    0.66
     jury
    0.66
     atrophy
    0.65
     pursuant
    0.63
     situated
    0.63
     ty
    0.63
    witt
    0.62
     Grunds
    0.61
    ὤ
    0.61
    Activations Density 0.062%

    No Known Activations