© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112679
    Prev
    Next
    INDEX
    Explanations

    September and related words

    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
    ↵↵
    -2.89
     وإ
    -2.52
     captivated
    -2.27
     upbeat
    -2.25
     Nicht
    -2.20
     wenn
    -2.20
    ел
    -2.13
     envió
    -2.13
     —
    -2.11
    ну
    -2.11
    POSITIVE LOGITS
    n
    3.03
    e
    2.97
    d
    2.77
    昞
    2.69
    ization
    2.52
    síða
    2.52
    Ꮵ
    2.48
    ांकि
    2.41
    鯡
    2.39
    b
    2.23
    Activations Density 0.012%

    No Known Activations