© 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. 130085
    Prev
    Next
    INDEX
    Explanations

    according to

    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
    子は
    -2.89
    子が
    -2.59
    はかなり
    -2.16
     پنجم
    -2.14
    子さん
    -2.14
     في
    -2.14
    は約
    -2.05
    がとても
    -2.02
    は
    -1.94
    が
    -1.94
    POSITIVE LOGITS
    なんだろう
    2.19
    予定です
    2.16
    なのかな
    1.96
    ところです
    1.91
    様です
    1.89
    なのでしょう
    1.80
    なのだ
    1.74
    べし
    1.73
    ところに
    1.73
     or
    1.66
    Activations Density 97.473%

    No Known Activations