© 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. 10-GEMMASCOPE-RES-131K
    7. 173
    Prev
    Next
    INDEX
    Explanations

    .com

    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_10/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
     on
    -2.92
     or
    -2.70
     in
    -2.63
     and
    -2.34
     at
    -2.25
     by
    -2.25
     that
    -2.03
     when
    -2.00
     other
    -1.98
     with
    -1.95
    POSITIVE LOGITS
    苼
    1.99
     véhicules
    1.97
    綃
    1.94
    賸
    1.88
     própri
    1.84
    蹓
    1.79
    日産
    1.76
     ſon
    1.72
     現貨
    1.69
     perpé
    1.66
    Activations Density 0.088%

    No Known Activations