© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 8046
    Prev
    Next
    INDEX
    Explanations

    words ending in -ation or -igation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    IENCE
    0.50
    OCKET
    0.48
    ្រី
    0.47
    <unused202>
    0.46
    繁忙時間服務
    0.46
    ンス
    0.45
     posição
    0.45
    ียบ
    0.45
     avión
    0.45
    ួរ
    0.45
    POSITIVE LOGITS
    n
    0.54
    ally
    0.53
    ary
    0.53
    ist
    0.47
    als
    0.44
     бушлай
    0.44
    פ
    0.44
    보다는
    0.43
    ne
    0.42
     Museums
    0.42
    Activations Density 0.099%

    No Known Activations