© 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. 118806
    Prev
    Next
    INDEX
    Explanations

    Ismail, ISMA, ISM, Islet

    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
    姽
    -3.44
    ⑊
    -3.39
    ఽ
    -3.38
    ︲
    -3.36
    圌
    -3.34
    踯
    -3.34
    蓠
    -3.20
    讠
    -3.05
    ſſen
    -3.03
    actéristi
    -3.02
    POSITIVE LOGITS
     This
    3.75
     What
    3.39
     There
    3.17
     “
    3.11
     in
    2.81
     Aside
    2.50
     At
    2.47
     During
    2.45
     Perhaps
    2.41
     这
    2.41
    Activations Density 0.038%

    No Known Activations