© 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. 70241
    Prev
    Next
    INDEX
    Explanations

    enabling or causing

    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
    Mereka
    -1.41
    ziert
    -1.39
     knew
    -1.30
     ยาว
    -1.24
     by
    -1.24
     have
    -1.24
     would
    -1.22
    çons
    -1.21
     Einige
    -1.21
     may
    -1.20
    POSITIVE LOGITS
     your
    2.03
     which
    1.47
    踮
    1.46
     savait
    1.45
     ۱۸
    1.38
     vorige
    1.36
    苤
    1.33
    фикация
    1.30
     fichiers
    1.29
     ۱۳
    1.27
    Activations Density 0.055%

    No Known Activations