© 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. 58414
    Prev
    Next
    INDEX
    Explanations

    names and biological pathways

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

    biblical names and religious references, particularly from the Old Testament.

    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
    éviter
    -1.60
     功效
    -1.59
    entistas
    -1.58
    퐿
    -1.52
    liques
    -1.51
     saada
    -1.48
    ваясь
    -1.46
    これらの
    -1.45
     verminder
    -1.45
    鵺
    -1.43
    POSITIVE LOGITS
     l
    1.70
    .
    1.66
    </td>
    1.64
     [
    1.55
     n
    1.51
     u
    1.43
     “
    1.43
     t
    1.43
     p
    1.40
     For
    1.40
    Activations Density 0.012%

    No Known Activations