© 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. 9479
    Prev
    Next
    INDEX
    Explanations

    common or general purpose

    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
    はもちろん
    -1.36
    følge
    -1.33
     Kerja
    -1.25
    timation
    -1.24
    遽
    -1.23
     tiga
    -1.23
    忖
    -1.23
     incarnation
    -1.21
     bluza
    -1.20
    itizing
    -1.20
    POSITIVE LOGITS
    8
    1.95
    5
    1.73
     general
    1.71
    7
    1.48
    4
    1.38
    a
    1.38
    >
    1.38
    9
    1.37
    f
    1.34
    general
    1.33
    Activations Density 0.082%

    No Known Activations