© 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. 72395
    Prev
    Next
    INDEX
    Explanations

    promising areas, prospects, and materials

    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
     a
    -2.34
     katkı
    -2.27
     we
    -2.20
     asisten
    -2.13
     recopila
    -2.06
    𖣘
    -2.06
     Öffnen
    -2.05
    翆
    -2.05
    "..."
    -1.95
    の中に
    -1.95
    POSITIVE LOGITS
    ・・。
    2.23
     一起
    1.98
     這
    1.98
     工場
    1.88
     –
    1.88
     виро
    1.84
    聼
    1.81
    ."
    1.80
     块
    1.78
     promising
    1.77
    Activations Density 0.010%

    No Known Activations