© 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. 112229
    Prev
    Next
    INDEX
    Explanations

    being considered or contrasted

    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
     exitosa
    -1.27
     Partager
    -1.25
     Répondre
    -1.24
     Meilleures
    -1.24
    vestidos
    -1.24
     långt
    -1.22
     úspě
    -1.22
    хіво
    -1.20
     lezen
    -1.19
     Coloque
    -1.16
    POSITIVE LOGITS
    ης
    1.34
    sburg
    1.28
     and
    1.18
     itself
    1.13
    代言
    1.13
    !
    1.07
    多くの
    1.06
    mení
    1.05
    äule
    1.03
    8
    1.03
    Activations Density 0.416%

    No Known Activations