© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33304
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns and determiners

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

    The neuron is keyed to detect numeric tokens—years, measurements, percentages, citation numbers, and other digit-based data.

    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
    ednesday
    -1.33
     endeavouring
    -1.06
     ausein
    -1.00
     endeav
    -0.99
     Potassium
    -0.98
     Ultrasound
    -0.98
    Allemagne
    -0.97
     클
    -0.96
    TypedDataSet
    -0.96
    ⮞
    -0.96
    POSITIVE LOGITS
     these
    2.88
     this
    1.99
    these
    1.80
     tersebut
    1.72
     such
    1.61
     этих
    1.54
    These
    1.54
     These
    1.50
    这些
    1.38
     those
    1.36
    Activations Density 0.320%

    No Known Activations