© 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. 22-GEMMASCOPE-RES-131K
    7. 128234
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     because
    -1.27
     only
    -1.20
     through
    -1.16
     on
    -1.11
     after
    -1.11
     Only
    -1.09
     Unlike
    -1.07
     extravagant
    -1.03
     since
    -1.03
     should
    -1.03
    POSITIVE LOGITS
     可愛い
    0.99
     赤ちゃん
    0.95
     praticamente
    0.90
     Möglichkeit
    0.89
     Promotes
    0.89
     다른
    0.88
     demais
    0.88
     possibilità
    0.88
     afore
    0.86
     другие
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.