© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208089
    Prev
    Next
    INDEX
    Explanations

    taking or arising after era

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

    Chinese, Japanese, Korean, and other scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    עם
    0.47
    '
    0.44
     fotografia
    0.44
     observar
    0.43
     brow
    0.42
     ră
    0.41
     connaît
    0.41
     러
    0.41
     lebt
    0.41
     cere
    0.40
    POSITIVE LOGITS
     ष
    0.47
    hehi
    0.45
     prohibiting
    0.45
    调度
    0.45
    会出现
    0.44
    枳
    0.44
    蒌
    0.44
    seur
    0.44
    起始
    0.43
     Sekret
    0.43
    Activations Density 0.001%

    No Known Activations