© 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. 22-GEMMASCOPE-RES-131K
    4. 68237
    Prev
    Next
    INDEX
    Explanations

    code block structure

    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
     dedans
    -1.04
    ベント
    -0.85
     igno
    -0.85
    無し
    -0.83
     gafas
    -0.83
     Mondiale
    -0.82
     venezia
    -0.82
     PEI
    -0.82
     mensagens
    -0.81
    ici
    -0.80
    POSITIVE LOGITS
     staring
    0.83
    bares
    0.79
    Xinhua
    0.78
    ТВ
    0.78
    襲
    0.77
    ixels
    0.76
    w
    0.76
     by
    0.75
    OrDefault
    0.74
    では
    0.73
    Activations Density 0.007%

    No Known Activations