© 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. 70535
    Prev
    Next
    INDEX
    Explanations

    image captions and descriptions

    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
    ᱼ
    -1.33
    espół
    -1.06
    おはよう
    -1.05
     Malone
    -1.04
     Dray
    -1.02
    涣
    -1.02
    США
    -1.02
    nemia
    -1.01
     OTHERS
    -1.01
    ᐉ
    -1.00
    POSITIVE LOGITS
     a
    1.40
     the
    1.20
    some
    1.16
     result
    1.06
    item
    1.04
     nuevos
    1.02
     results
    1.00
     результа
    0.98
     entire
    0.96
     The
    0.95
    Activations Density 0.012%

    No Known Activations