© 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. 10-GEMMASCOPE-RES-131K
    4. 69475
    Prev
    Next
    INDEX
    Explanations

    section and document beginnings

    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
     nieve
    -1.90
    ↓
    -1.73
    凩
    -1.67
    馓
    -1.56
     diverses
    -1.55
     %.
    -1.55
     pernic
    -1.55
    瘣
    -1.55
     anun
    -1.54
     pengar
    -1.54
    POSITIVE LOGITS
    :
    2.19
     our
    1.93
     $
    1.68
     begin
    1.66
     Having
    1.66
    </strong>
    1.64
    Having
    1.60
     having
    1.59
     These
    1.57
     BOTH
    1.53
    Activations Density 0.009%

    No Known Activations