© 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. 44111
    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
     OGSÅ
    -1.39
     márm
    -1.34
    ューズ
    -1.33
     tkan
    -1.28
     achet
    -1.26
     químico
    -1.23
    enteri
    -1.23
     exé
    -1.23
     lured
    -1.23
     heartbroken
    -1.21
    POSITIVE LOGITS
    1
    1.95
     to
    1.52
    8
    1.52
    7
    1.46
    を
    1.40
    2
    1.39
    0
    1.26
    4
    1.21
    _
    1.19
    6
    1.19
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.