© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 61277
    Prev
    Next
    INDEX
    Explanations

    half

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ígono
    0.42
    رل
    0.40
     matériel
    0.38
    γραφή
    0.36
    ensee
    0.35
    ថ្ងៃ
    0.35
    Genuine
    0.35
    getFile
    0.34
    <unused12>
    0.34
    ᙱ
    0.34
    POSITIVE LOGITS
     half
    3.52
     Half
    3.09
    Half
    3.08
    half
    3.03
     HALF
    2.77
     نصف
    2.61
    HALF
    2.61
     полови
    2.56
     setengah
    2.56
    半
    2.55
    Activations Density 0.002%

    No Known Activations