© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38904
    Prev
    Next
    INDEX
    Explanations

    places and races

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     that
    -1.80
     creating
    -1.61
     having
    -1.60
     their
    -1.59
     without
    -1.58
     very
    -1.58
     commonly
    -1.54
     usually
    -1.53
     what
    -1.52
     as
    -1.48
    POSITIVE LOGITS
     Dinas
    1.37
     ſont
    1.27
     après
    1.27
     alluring
    1.25
     "~
    1.21
    鸸
    1.21
     verhind
    1.20
    蛱
    1.20
    
    1.19
     Après
    1.18
    Activations Density 0.003%

    No Known Activations