© 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. 81659
    Prev
    Next
    INDEX
    Explanations

    oh my

    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
     Haush
    -0.77
     jeg
    -0.72
     Illinois
    -0.71
     Volvo
    -0.71
     Gleich
    -0.71
     Afro
    -0.69
     fasteners
    -0.69
    になりたい
    -0.68
     Kiedy
    -0.68
    嫌い
    -0.68
    POSITIVE LOGITS
     My
    2.61
     my
    2.55
    My
    2.11
    my
    1.89
     MY
    1.84
    MY
    1.63
    我的
    1.52
    getMy
    1.50
     我的
    1.44
    mig
    1.34
    Activations Density 0.016%

    No Known Activations