© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130218
    Prev
    Next
    INDEX
    Explanations

    Q/Dirección/Anterior/Horiz

    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
    .
    -1.88
    ations
    -1.84
    ちゃんと
    -1.84
    ︲
    -1.82
     desse
    -1.81
    榀
    -1.77
    聍
    -1.77
     reloadData
    -1.73
     migh
    -1.73
    濺
    -1.71
    POSITIVE LOGITS
    ي
    3.16
    い
    2.50
    й
    2.38
    ি
    2.08
    asanjo
    2.06
    ी
    1.98
    י
    1.96
    }\
    1.92
    ]-\
    1.91
     パネル
    1.90
    Activations Density 0.000%

    No Known Activations