© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84166
    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
    薷
    -1.30
     interfaz
    -1.17
    髫
    -1.16
     ſol
    -1.16
    ⌵
    -1.15
     vektor
    -1.13
    ㉒
    -1.13
     teolog
    -1.13
    possibly
    -1.12
    镲
    -1.11
    POSITIVE LOGITS
     often
    1.25
     changed
    1.24
     really
    1.19
     mainly
    1.17
     most
    1.16
     definitely
    1.16
     usually
    1.14
     change
    1.09
     difficult
    1.09
     considerably
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.