© 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. 9281
    Prev
    Next
    INDEX
    Explanations

    rotate

    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
    ícone
    -1.33
     theses
    -1.31
     Deiner
    -1.30
     these
    -1.26
    lcccccc
    -1.24
     Gewinner
    -1.23
     erfolgre
    -1.20
    outros
    -1.19
     poissons
    -1.19
     этих
    -1.16
    POSITIVE LOGITS
     in
    1.36
     again
    1.34
    ⍝
    1.16
     the
    1.12
     something
    1.09
    ﺯ
    1.09
     novamente
    1.07
     nuevamente
    1.06
    complished
    1.03
    actment
    1.03
    Activations Density 0.070%

    No Known Activations