© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70186
    Prev
    Next
    INDEX
    Explanations

    purpose or plan

    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
    ized
    -2.75
     differing
    -2.31
    ically
    -2.25
    蟥
    -2.03
    N
    -2.02
     Перейти
    -2.00
     «
    -2.00
     conjunction
    -1.99
     ६
    -1.97
     contrasting
    -1.95
    POSITIVE LOGITS
    .”
    2.64
    乀
    2.58
    ⚣
    2.31
     they
    2.27
    啬
    2.16
    犼
    2.13
    了你
    2.02
     estoque
    1.99
     CALIFORNI
    1.95
    ᕱ
    1.95
    Activations Density 0.005%

    No Known Activations