© 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. 34-GEMMASCOPE-RES-131K
    7. 32915
    Prev
    Next
    INDEX
    Explanations

    in the making or decision making

    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_34/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
     Erzä
    -0.73
    cinhas
    -0.71
    alleria
    -0.69
    Ngay
    -0.69
    iach
    -0.68
    зора
    -0.67
     Gesetzes
    -0.67
     pembayaran
    -0.67
    پا
    -0.66
    瀬戸
    -0.63
    POSITIVE LOGITS
     making
    5.00
    making
    4.47
    Making
    3.94
     Making
    3.73
    MAKING
    3.31
     MAKING
    3.19
     mak
    2.48
     makin
    2.47
    make
    2.31
     creation
    2.25
    Activations Density 0.042%

    No Known Activations