© 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. 103565
    Prev
    Next
    INDEX
    Explanations

    special characters and following words

    np_acts-logits-general · gemini-2.5-flash-lite

    double quotation marks that end quoted text or titles.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    0
    -3.78
    1
    -3.66
    नलोड
    -3.06
    鷓
    -3.03
    ～～～
    -3.03
    趼
    -2.92
    囖
    -2.89
    ～～
    -2.84
    啰
    -2.75
    3
    -2.72
    POSITIVE LOGITS
    ’
    3.50
    癰
    3.14
    籥
    3.11
    蹰
    2.97
     cũng
    2.94
    蓥
    2.94
    踽
    2.88
    釹
    2.86
     ,‬
    2.80
    𝒮
    2.77
    Activations Density 0.002%

    No Known Activations