© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 9885
    Prev
    Next
    INDEX
    Explanations

    Reuters news articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     composés
    0.45
    絫
    0.43
    窑
    0.40
     Oxidation
    0.39
    濬
    0.39
    严重的
    0.39
    ➫
    0.39
     oxidation
    0.38
    ལ
    0.38
    高兴
    0.38
    POSITIVE LOGITS
    Reuters
    1.47
     Reuters
    1.46
     Thomson
    0.55
     RE
    0.52
    Thom
    0.47
     Bloomberg
    0.41
    Bloomberg
    0.41
    🥈
    0.40
    RE
    0.39
    qa
    0.38
    Activations Density 0.004%

    No Known Activations