© 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. 10-GEMMASCOPE-RES-131K
    7. 130762
    Prev
    Next
    INDEX
    Explanations

    computing expressions or definitions

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

    The neuron activates on numeric tokens (numbers and numeric literals).

    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
    ṕ
    -1.56
     its
    -1.39
    Elő
    -1.31
     lavable
    -1.30
     alfabeto
    -1.29
     turista
    -1.29
     aking
    -1.27
    jourd
    -1.27
     pertinente
    -1.27
     diriger
    -1.26
    POSITIVE LOGITS
     nuevamente
    1.52
    0
    1.45
     began
    1.45
     has
    1.42
     more
    1.41
     without
    1.38
     After
    1.37
     However
    1.35
     When
    1.34
     from
    1.33
    Activations Density 0.000%

    No Known Activations