© 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. 111328
    Prev
    Next
    INDEX
    Explanations

    many

    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
    了几
    -1.38
    了很多
    -1.33
    是要
    -1.29
    に関して
    -1.27
     were
    -1.27
    另一
    -1.27
    weł
    -1.23
     більше
    -1.19
     gjelder
    -1.17
     apparti
    -1.16
    POSITIVE LOGITS
     of
    2.94
     our
    1.71
     других
    1.59
    ของ
    1.59
    九年
    1.52
    𝒓
    1.48
     yPos
    1.48
     []:
    1.47
     italianos
    1.45
    й
    1.45
    Activations Density 0.054%

    No Known Activations