© 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. 19598
    Prev
    Next
    INDEX
    Explanations

    negative outcomes or extremes

    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
    他们在
    -1.23
     tremend
    -1.18
     precis
    -1.13
    更为
    -1.13
     prénom
    -1.05
    但我
    -1.03
     masih
    -0.99
     demostr
    -0.98
    sugges
    -0.98
     lebih
    -0.98
    POSITIVE LOGITS
     until
    1.41
     Until
    1.27
     fueran
    1.18
    følgelig
    1.13
     become
    1.12
     Sometimes
    1.09
    ēd
    1.07
     *)&
    1.05
    为止
    1.05
    ädig
    1.04
    Activations Density 0.052%

    No Known Activations