© 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. 22-GEMMASCOPE-RES-131K
    7. 72973
    Prev
    Next
    INDEX
    Explanations

    medical assessment and evaluation

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

    terms related to assessments, evaluations, and screenings in professional or medical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron primarily detects numeric measurements and quantities (e.g., counts, percentages, and other numeral values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ,
    -1.10
     comparten
    -1.05
     deseado
    -1.02
    .
    -1.01
     comenzará
    -0.99
    </i>
    -0.98
    ↵
    -0.97
    essayer
    -0.97
     esteemed
    -0.96
     依
    -0.94
    POSITIVE LOGITS
     and
    1.55
    ֵּ
    1.37
     assessment
    1.33
     before
    1.30
     assessments
    1.13
     penilaian
    1.13
    ֶּ
    1.11
     kredit
    1.10
     milliard
    1.10
     evaluation
    1.09
    Activations Density 0.073%

    No Known Activations