© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 87252
    Prev
    Next
    INDEX
    Explanations

    widget app Windows

    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
    那人
    -1.06
     by
    -0.97
    ussia
    -0.83
     peut
    -0.81
    почка
    -0.81
     Unterstüt
    -0.80
     that
    -0.80
    Mozart
    -0.79
     Haush
    -0.79
     Kenyan
    -0.79
    POSITIVE LOGITS
    widget
    1.41
     widget
    1.12
     with
    1.01
    jähriger
    0.91
    Widget
    0.88
     widgets
    0.88
    TABLE
    0.81
    ILLE
    0.80
    COOH
    0.80
     Hombre
    0.79
    Activations Density 0.001%

    No Known Activations