© 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. 41787
    Prev
    Next
    INDEX
    Explanations

    places and systems

    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
     nieco
    -1.48
     sollten
    -1.45
     about
    -1.42
     etwa
    -1.38
    if
    -1.34
     nachdem
    -1.31
     swojego
    -1.30
     dwóch
    -1.30
     into
    -1.29
     tinha
    -1.26
    POSITIVE LOGITS
     that
    1.92
    Setiap
    1.41
     each
    1.30
    alı
    1.28
     the
    1.25
    tersebut
    1.15
    Greatest
    1.13
     cias
    1.12
    eventos
    1.12
    Beberapa
    1.12
    Activations Density 0.201%

    No Known Activations