© 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
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 15232
    Prev
    Next
    INDEX
    Explanations

    New York, Kolkata, Cornell University

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

    places and regions

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

    Looking at the activations, this neuron activates strongly on: - Possessive constructions with apostrophes (Village Clerk**'s**, driver**'s**, owner**'s**) - References to specific locations/jurisdictions (Village of Hempstead

    oai_token-act-pair · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ěl
    0.61
     المشروع
    0.59
     المقسوم
    0.59
     искусство
    0.58
    یتے
    0.57
    威尔
    0.56
     überzeugt
    0.55
     zählen
    0.55
    ě
    0.55
    ŷ
    0.55
    POSITIVE LOGITS
     {
    0.77
     Adirond
    0.70
     Schenectady
    0.68
     :
    0.67
     with
    0.65
    -{
    0.65
    ham
    0.61
    /:
    0.61
     without
    0.60
     Buffalo
    0.60
    Activations Density 0.379%

    No Known Activations