© 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. 47898
    Prev
    Next
    INDEX
    Explanations

    documentation tags and parameters

    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
     古着
    -1.04
     houſe
    -1.02
     immense
    -0.96
     beinahe
    -0.96
     vermutlich
    -0.96
     booming
    -0.95
     Ancak
    -0.92
     gewöhnlich
    -0.91
    ANDY
    -0.91
     numerous
    -0.90
    POSITIVE LOGITS
     does
    0.91
     (
    0.90
     accessor
    0.89
    dataGridView
    0.88
     gjelder
    0.87
     érté
    0.87
     méthode
    0.86
     also
    0.84
    Get
    0.84
    держка
    0.82
    Activations Density 0.013%

    No Known Activations