© 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. 49258
    Prev
    Next
    INDEX
    Explanations

    accessing object properties or calling methods

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

    The neuron activates on numeric literals (digits or numbers) in the text.

    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
     meraih
    -1.35
    ebly
    -1.31
     Apesar
    -1.30
     memenangkan
    -1.27
     Embora
    -1.27
     både
    -1.23
     dikutip
    -1.20
     vlož
    -1.18
     ensimmä
    -1.18
     melawan
    -1.16
    POSITIVE LOGITS
     =
    1.72
     set
    1.52
     said
    1.48
     certainly
    1.41
    is
    1.36
     will
    1.33
     likely
    1.33
     surely
    1.27
     added
    1.27
     need
    1.27
    Activations Density 0.014%

    No Known Activations