© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73748
    Prev
    Next
    INDEX
    Explanations

    bio- prefix

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

    the prefix "bio-" and related biological/scientific terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    基本的に
    -1.70
    塒
    -1.55
     totalling
    -1.55
    虓
    -1.54
     nahezu
    -1.48
     to
    -1.45
     flavours
    -1.45
     meest
    -1.44
     необходи
    -1.43
    思議
    -1.43
    POSITIVE LOGITS
    뚤
    1.76
    s
    1.67
    bio
    1.62
    ⾳
    1.60
    摃
    1.59
    鸫
    1.55
    ኧ
    1.54
    んびり
    1.53
    biological
    1.51
    んび
    1.51
    Activations Density 0.094%

    No Known Activations