© 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. 34-GEMMASCOPE-RES-131K
    7. 77991
    Prev
    Next
    INDEX
    Explanations

    whole blood

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

    scientific text describing experiments with biological samples, fluids, or tissues.

    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_34/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
    EMERG
    -0.76
     danh
    -0.75
    baller
    -0.75
    ciencia
    -0.75
    apos
    -0.75
    gettyimages
    -0.71
    不吃
    -0.71
     McF
    -0.70
    getUserName
    -0.69
    ཏ
    -0.69
    POSITIVE LOGITS
     whole
    3.05
    Whole
    2.88
    whole
    2.88
     Whole
    2.61
     WHOLE
    1.94
    Term
    1.61
     Term
    1.58
     ganzen
    1.48
     ganze
    1.48
     term
    1.41
    Activations Density 0.094%

    No Known Activations