© 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. 16-GEMMASCOPE-2-RES-262K
    7. 87007
    Prev
    Next
    INDEX
    Explanations

    reduction or reducible

    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_16_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
    ä
    0.73
    וף
    0.73
     ఉపయోగ
    0.66
     erweit
    0.66
     huyện
    0.63
     革
    0.63
     መጠቀም
    0.62
     использование
    0.61
    වීම
    0.60
     europäischen
    0.59
    POSITIVE LOGITS
    ล
    0.68
    ;
    0.64
    ),
    0.63
    ลด
    0.62
     Reduced
    0.59
    2
    0.59
     reduced
    0.58
    秕
    0.58
    ক
    0.57
    Οι
    0.57
    Activations Density 0.009%

    No Known Activations