© 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. 14702
    Prev
    Next
    INDEX
    Explanations

    nutrition, therapy, and language professions

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

    The main thing this neuron does is find mentions of allied‐health professions and nutrition‐related credentials (e.g., dietetics, nutrition therapy, speech‐language pathology).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     ")";
    -1.50
     yılında
    -1.44
    klara
    -1.36
    getStatus
    -1.34
     algunos
    -1.31
     SOME
    -1.29
     menjadi
    -1.29
    
    -1.28
     $
    -1.28
     */
    -1.27
    POSITIVE LOGITS
    </b>
    1.70
    </h1>
    1.65
    描いた
    1.54
     soportes
    1.52
    のおかげ
    1.51
    涐
    1.51
    様な
    1.48
    様に
    1.48
     than
    1.42
     нашел
    1.40
    Activations Density 0.014%

    No Known Activations