© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 16120
    Prev
    Next
    INDEX
    Explanations

    home safety, environment, or network

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

    The neuron fires strongly on the word “home” (and close compounds like “home-cooked” or “at home”), i.e. references to “home.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
     géographique
    1.06
    Meine
    1.05
    ان
    1.04
    ن
    1.00
    س
    1.00
    на
    0.99
     verdes
    0.98
    ρα
    0.95
     Leur
    0.94
    straße
    0.93
    POSITIVE LOGITS
     or
    1.06
     hoặc
    1.03
    或者
    0.98
    或
    0.97
     या
    0.95
    หรือ
    0.95
     কিংবা
    0.95
     અથવા
    0.94
     ή
    0.93
    /
    0.93
    Activations Density 0.225%

    No Known Activations