© 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. 68211
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    1
    -3.92
    the
    -3.66
    7
    -3.61
    8
    -3.30
    6
    -3.25
    4
    -3.19
    2
    -3.17
    a
    -3.14
    5
    -3.11
    9
    -2.98
    POSITIVE LOGITS
     Which
    3.66
     not
    2.95
    眨眼
    2.63
     We
    2.59
     now
    2.52
     interpreta
    2.44
     detecta
    2.36
     During
    2.36
     Even
    2.34
    Cdb
    2.33
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.