© 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. 25820
    Prev
    Next
    INDEX
    Explanations

    function declaration or implementation

    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
     焼肉
    -0.78
    ായ
    -0.77
     setelah
    -0.75
     edifici
    -0.75
    最初は
    -0.75
    телей
    -0.75
    Maison
    -0.73
    resourceId
    -0.73
    IsTrue
    -0.72
     Ortsteil
    -0.72
    POSITIVE LOGITS
     Stainless
    0.86
    Sharon
    0.82
    Ц
    0.79
    З
    0.78
    Со
    0.77
    Köszi
    0.76
    І
    0.76
    PACE
    0.76
    Stan
    0.75
     dátum
    0.75
    Activations Density 0.007%

    No Known Activations