© 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. 59330
    Prev
    Next
    INDEX
    Explanations

    auriculatum, administration, junction, acid

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

    the word stem 'ric' as it appears in scientific or medical terminology.

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

    This neuron responds to the letter sequence “ric” appearing anywhere inside a word.

    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
    a
    -3.58
    ?
    -3.28
    e
    -2.88
    ا
    -2.78
    am
    -2.75
    “
    -2.69
    也将
    -2.64
    ent
    -2.64
    2
    -2.61
    al
    -2.53
    POSITIVE LOGITS
    颙
    2.95
    ric
    2.81
     französische
    2.69
    我没
    2.58
     verbess
    2.55
    沺
    2.41
    
    2.33
    悒
    2.31
     și
    2.30
    鹛
    2.30
    Activations Density 0.013%

    No Known Activations