© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39651
    Prev
    Next
    INDEX
    Explanations

    piece or Pc Set

    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
    啕
    -2.03
    ша
    -1.99
     &
    -1.96
    〬
    -1.88
    毟
    -1.83
    能
    -1.82
     Privacidad
    -1.80
    ༷
    -1.73
     itſelf
    -1.72
     inextrica
    -1.70
    POSITIVE LOGITS
    P
    2.27
    кой
    2.22
    饪
    2.20
    汌
    2.16
    ⛛
    2.00
    篥
    1.95
    ꝛ
    1.91
    </strong>
    1.85
    かっこいい
    1.84
    </em>
    1.82
    Activations Density 0.012%

    No Known Activations