© 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. 10-GEMMASCOPE-RES-131K
    7. 21896
    Prev
    Next
    INDEX
    Explanations

    specifying isolation or a single condition

    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
     are
    -1.59
     perfekte
    -1.58
     добавил
    -1.56
     aktuelle
    -1.48
    1
    -1.46
    geſ
    -1.44
     konkrete
    -1.37
     traditionelle
    -1.31
     that
    -1.29
    4
    -1.29
    POSITIVE LOGITS
    ሖ
    1.75
    了一声
    1.67
    ङ
    1.66
     reason
    1.59
    ✼
    1.52
    function
    1.48
    に変
    1.47
    ベーション
    1.47
     maternelle
    1.45
     magnétique
    1.45
    Activations Density 0.025%

    No Known Activations