© 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. 8107
    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
     required
    -1.17
     used
    -1.16
     using
    -1.09
     explicitly
    -1.09
     even
    -1.08
     unruly
    -1.07
     actually
    -1.06
     fairly
    -1.05
     If
    -1.04
     stating
    -1.04
    POSITIVE LOGITS
     nieuwe
    1.24
    projek
    1.11
     pratiquer
    1.09
     personnages
    1.05
    played
    1.03
    sounds
    1.03
    ercises
    1.03
     zoude
    1.02
    他们
    1.01
    dengan
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.