© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19199
    Prev
    Next
    INDEX
    Explanations

    titles that begin phrases

    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_10/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
    疍
    -1.52
    醅
    -1.50
     grosse
    -1.50
    餍
    -1.50
    њу
    -1.47
    饹
    -1.45
    ello
    -1.44
    tières
    -1.43
     specta
    -1.42
    teryx
    -1.42
    POSITIVE LOGITS
     kind
    1.33
     sets
    1.33
     we
    1.27
     şeyler
    1.26
     area
    1.17
     set
    1.17
     aanwezig
    1.17
     and
    1.16
     markiert
    1.15
    ↵↵
    1.14
    Activations Density 0.002%

    No Known Activations