© 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. 21951
    Prev
    Next
    INDEX
    Explanations

    foreign negations or absences

    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
     sprüche
    -2.55
     somewhat
    -2.38
    禤
    -2.17
    骉
    -2.14
    糴
    -2.13
     卡通
    -2.06
     图库
    -2.03
     also
    -1.99
     heo
    -1.95
     aranha
    -1.92
    POSITIVE LOGITS
    1
    2.17
    2
    1.98
    AutoresizingMask
    1.98
    What
    1.82
    5
    1.79
    ção
    1.75
    錞
    1.72
    \{
    1.70
    fficking
    1.70
    ें
    1.68
    Activations Density 0.003%

    No Known Activations