© 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. 85247
    Prev
    Next
    INDEX
    Explanations

    unit/item indicators

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

    The neuron is detecting numeric measurements and quantities (amounts and units) in recipe instructions.

    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
     your
    -1.63
    entlichen
    -1.45
    rías
    -1.31
    呖
    -1.31
    お母
    -1.31
     entret
    -1.31
     him
    -1.28
    Untuk
    -1.23
    图源
    -1.23
     Which
    -1.22
    POSITIVE LOGITS
     if
    1.55
     again
    1.48
     frische
    1.34
     first
    1.31
     as
    1.30
    頃から
    1.28
     before
    1.24
     précédentes
    1.21
    俠
    1.20
    quarelle
    1.17
    Activations Density 0.012%

    No Known Activations