© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11908
    Prev
    Next
    INDEX
    Explanations

    genealogy and historical records

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

    birth certificates and records

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
    science
    0.44
    SCIENCE
    0.43
    Thoreau
    0.41
    ʏ
    0.41
    figures
    0.40
    Science
    0.40
    prf
    0.40
    danger
    0.39
    scient
    0.39
    襲
    0.39
    POSITIVE LOGITS
     Genealogy
    0.76
     genealogical
    0.75
     Genealogical
    0.71
     genealog
    0.71
     genealogy
    0.70
     marriage
    0.65
     registrations
    0.64
     Transcription
    0.64
     registros
    0.64
     marriages
    0.63
    Activations Density 0.174%

    No Known Activations