© 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. 39509
    Prev
    Next
    INDEX
    Explanations

    medical & scientific citations

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

    citation codes or reference identifiers that include numbers.

    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
     of
    -2.38
     this
    -1.99
     then
    -1.59
     This
    -1.56
    ใน
    -1.51
    この
    -1.48
     when
    -1.45
     can
    -1.41
    immen
    -1.41
    今回は
    -1.38
    POSITIVE LOGITS
     guantes
    1.81
     trhu
    1.66
     battre
    1.63
     acoged
    1.61
     rác
    1.59
    尨
    1.59
     pulseira
    1.56
    ongyang
    1.54
     Nähr
    1.53
    same
    1.52
    Activations Density 0.131%

    No Known Activations