© 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. 58788
    Prev
    Next
    INDEX
    Explanations

    code prefixes and punctuation

    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
    TAINMENT
    -0.76
     Mandal
    -0.73
    ملك
    -0.73
     لدى
    -0.72
    étrie
    -0.71
    INGS
    -0.70
     marten
    -0.70
    andal
    -0.70
     Scho
    -0.68
    orianCalendar
    -0.68
    POSITIVE LOGITS
    gui
    0.87
    GUI
    0.83
     prad
    0.81
    strafe
    0.81
     Property
    0.81
    olato
    0.81
    Property
    0.80
    titled
    0.79
     panela
    0.78
    controller
    0.77
    Activations Density 0.006%

    No Known Activations