© 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. 22-GEMMASCOPE-RES-131K
    7. 130053
    Prev
    Next
    INDEX
    Explanations

    institutions, places, or titles

    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_22/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
     it
    -1.39
    ৳
    -1.26
     what
    -1.20
    ってる
    -1.16
    ३
    -1.09
    ــــ
    -1.07
    ﱠ
    -1.06
    ってます
    -1.05
     how
    -1.04
    に挑戦
    -1.03
    POSITIVE LOGITS
    プリング
    1.18
     contextLoads
    1.16
    があり
    1.13
    APPENDICES
    1.09
    が
    1.05
    owi
    1.05
    zellen
    1.05
    Содержание
    1.04
    دانلود
    1.02
    參考資料
    1.02
    Activations Density 0.005%

    No Known Activations