© 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. 90112
    Prev
    Next
    INDEX
    Explanations

    documentation, names, and metadata

    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
     XLV
    -0.82
    HOLD
    -0.82
     calab
    -0.74
    aglio
    -0.72
     ہوا
    -0.71
     Willard
    -0.70
     biryani
    -0.70
     essentially
    -0.70
     lcd
    -0.69
     jeunesse
    -0.69
    POSITIVE LOGITS
    ilan
    0.82
     plate
    0.81
    fying
    0.79
    啕
    0.78
     Valentin
    0.78
    )->
    0.77
     bugs
    0.75
    tingly
    0.75
    ishi
    0.74
    togram
    0.74
    Activations Density 0.009%

    No Known Activations