© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76715
    Prev
    Next
    INDEX
    Explanations

    "expected" value or outcome

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

    The neuron fires on numeric literal tokens (whole numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     cuillère
    -0.95
     Pièces
    -0.88
     cercle
    -0.86
     compromis
    -0.83
     sirop
    -0.83
     chapitre
    -0.82
     mètre
    -0.82
     queso
    -0.82
    átka
    -0.81
    CTYPE
    -0.80
    POSITIVE LOGITS
     expected
    5.44
    expected
    4.19
    Expected
    3.80
     Expected
    3.75
     expect
    3.17
     expectation
    3.13
     expectations
    3.11
    EXPECTED
    3.11
     expecting
    2.83
     anticipated
    2.75
    Activations Density 0.074%

    No Known Activations