© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9451
    Prev
    Next
    INDEX
    Explanations

    vintage jet or his car

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

    This neuron detects numerical or quantitative expressions (digits or spelled‐out numbers) together with their associated descriptive terms (counts, measurements, model names, etc.).

    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
     to
    -1.27
     ">=
    -1.09
    鬓
    -1.00
    digarh
    -0.99
    ,
    -0.98
    רושלים
    -0.97
     quienes
    -0.95
     through
    -0.94
     szóci
    -0.94
     área
    -0.94
    POSITIVE LOGITS
     magnifiques
    1.41
     powerful
    1.27
     equipment
    1.21
     velha
    1.21
     duong
    1.19
    fortunately
    1.15
     cerâmica
    1.15
     silêncio
    1.13
     familières
    1.13
     equipped
    1.13
    Activations Density 0.185%

    No Known Activations