© 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. 39705
    Prev
    Next
    INDEX
    Explanations

    neighborhoods and places

    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
    ibility
    -1.54
    ícias
    -1.42
    rogens
    -1.41
    lograph
    -1.40
    vereignty
    -1.39
    ilty
    -1.37
    aneity
    -1.37
    yship
    -1.36
     ۱۷
    -1.34
    itisation
    -1.34
    POSITIVE LOGITS
     I
    1.18
     of
    1.16
     rodeado
    1.11
     area
    1.02
     skóra
    1.00
     дав
    0.97
    Према
    0.96
     Five
    0.94
     juncture
    0.93
     pintadas
    0.93
    Activations Density 0.045%

    No Known Activations