© 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. 31-GEMMASCOPE-2-RES-262K
    7. 168612
    Prev
    Next
    INDEX
    Explanations

    large words, multilingual counting

    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_31_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
    ”
    0.49
    р
    0.47
    "
    0.46
    жду
    0.45
    al
    0.45
    в
    0.45
     molde
    0.44
     fabri
    0.44
    ’
    0.44
     G
    0.42
    POSITIVE LOGITS
    बड़े
    0.53
     വലിയ
    0.50
     abo
    0.50
    ಎಂ
    0.48
     बड़ी
    0.48
     ஆனால்
    0.47
    <unused262>
    0.47
     Результа
    0.47
     नवी
    0.46
     Євро
    0.46
    Activations Density 0.002%

    No Known Activations