© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111557
    Prev
    Next
    INDEX
    Explanations

    Gunnera, Gunell, Gunvordahl, Gunathilaka

    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
     '
    -2.61
     ''
    -2.25
    b
    -2.05
     your
    -2.02
     '[
    -1.88
    </i>
    -1.87
    ':
    -1.84
    ﹶ
    -1.80
    -'
    -1.74
    /'
    -1.73
    POSITIVE LOGITS
      
    1.70
    ’,
    1.70
     and
    1.69
    ”,
    1.60
    ,’
    1.59
    tedì
    1.55
    ↵↵
    1.53
     presentada
    1.53
     комната
    1.52
    liosis
    1.52
    Activations Density 0.122%

    No Known Activations