© 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. 70899
    Prev
    Next
    INDEX
    Explanations

    current year documentation

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

    The neuron activates on numeric tokens—digits, numbers, and numeric literals—especially version numbers or measurements in code and technical 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_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
    Stap
    -0.96
    INGRED
    -0.93
     izquier
    -0.93
     manageable
    -0.92
    ન્
    -0.88
     ihnen
    -0.88
     prosecutors
    -0.86
     ябло
    -0.86
     they
    -0.86
    ratu
    -0.86
    POSITIVE LOGITS
    WHAT
    1.06
    AHUL
    0.99
    izarse
    0.98
    Need
    0.98
    AGED
    0.94
    ῖς
    0.91
     mondta
    0.91
    Atsauces
    0.91
    Justice
    0.91
    Here
    0.90
    Activations Density 0.213%

    No Known Activations