© 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. 60138
    Prev
    Next
    INDEX
    Explanations

    getUser or UIApplication method

    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
     They
    -2.41
    的
    -2.38
    是
    -2.31
    as
    -2.23
    a
    -2.23
    It
    -2.17
    to
    -2.13
     появля
    -2.02
    ское
    -2.00
     mediterranean
    -1.98
    POSITIVE LOGITS
     대해
    2.56
     princesas
    2.41
    がある
    2.38
     beliebtesten
    2.36
     jeopardi
    2.33
     mimic
    2.31
     häufigsten
    2.30
    簠
    2.27
     ส์
    2.27
    Bước
    2.25
    Activations Density 0.000%

    No Known Activations