© 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. 22323
    Prev
    Next
    INDEX
    Explanations

    lists of commas and explanations

    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
     dlaczego
    -1.61
    s
    -1.59
     craindre
    -1.53
     grosir
    -1.53
    お昼
    -1.52
    りましたが
    -1.49
    踐
    -1.49
     сразу
    -1.49
    0
    -1.48
    Они
    -1.45
    POSITIVE LOGITS
     to
    1.67
     rather
    1.66
    ⌯
    1.62
     unable
    1.56
     devoid
    1.55
    इटम
    1.53
     lacking
    1.49
    tences
    1.48
    ))->
    1.45
    なの
    1.43
    Activations Density 0.018%

    No Known Activations