© 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. 118290
    Prev
    Next
    INDEX
    Explanations

    variable initialization

    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
     previous
    -0.88
    落
    -0.88
     tuturor
    -0.82
    VISED
    -0.81
     fam
    -0.80
     débar
    -0.77
     itself
    -0.77
    掉
    -0.75
     viceversa
    -0.75
    Cuer
    -0.75
    POSITIVE LOGITS
     aún
    0.97
     ещё
    0.87
    still
    0.84
     still
    0.83
     todavía
    0.82
    Then
    0.79
    izace
    0.79
    hoga
    0.79
     еще
    0.78
     ještě
    0.77
    Activations Density 0.003%

    No Known Activations