© 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. 73289
    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
    the
    -1.26
     if
    -1.05
     jeśli
    -1.03
     stout
    -1.00
     for
    -0.99
    t
    -0.99
    if
    -0.98
    ist
    -0.97
     S
    -0.96
    el
    -0.96
    POSITIVE LOGITS
     mauva
    1.32
     burch
    1.27
     felpa
    1.25
     itſelf
    1.22
     gallina
    1.20
     auffi
    1.19
     素描
    1.19
     marino
    1.16
     siena
    1.16
     ufe
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.