© 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. 39883
    Prev
    Next
    INDEX
    Explanations

    maxillofacial, Weill Cornell, papillomas

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

    the letters "ill" in anatomical or medical terms.

    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
    an
    -2.63
    る
    -2.48
    He
    -2.47
     ſte
    -2.47
     fulfil
    -2.31
    感じです
    -2.30
    ･･
    -2.23
    However
    -2.23
    er
    -2.22
     disdain
    -2.20
    POSITIVE LOGITS
    l
    3.08
    oughby
    3.06
    柃
    2.97
    柺
    2.75
    琑
    2.72
    镦
    2.64
    鸰
    2.63
     itſelf
    2.61
    栳
    2.59
    ſſen
    2.58
    Activations Density 0.035%

    No Known Activations