© 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. 99504
    Prev
    Next
    INDEX
    Explanations

    German, Russian, Dutch, French, Japanese, English

    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
     был
    -2.19
     refrigerador
    -1.90
    After
    -1.88
    初めての
    -1.88
    ！）
    -1.86
     его
    -1.84
     personalizadas
    -1.79
    ,\\
    -1.78
    When
    -1.74
    <bos>
    -1.73
    POSITIVE LOGITS
     the
    2.25
     durer
    1.99
     agir
    1.79
    癭
    1.77
    踭
    1.77
     They
    1.74
    と言われて
    1.74
    狃
    1.73
     mauva
    1.73
     zonder
    1.72
    Activations Density 0.002%

    No Known Activations