© 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. 16172
    Prev
    Next
    INDEX
    Explanations

    call or vegetation

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

    This neuron fires on the personal or organizational names following “owned by,” i.e. the owner names in property‐ownership listings.

    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
    ರುವ
    0.87
    ма
    0.85
     ovaj
    0.79
    0
    0.77
    ></
    0.75
    '
    0.74
    شر
    0.72
    ुन
    0.72
    がい
    0.72
    yaa
    0.72
    POSITIVE LOGITS
     Anwendungen
    0.84
     라고
    0.74
     嗯
    0.73
     съем
    0.72
     प्रतिबिंब
    0.71
    䡆
    0.70
     Anlagen
    0.70
     Elektrokhimiya
    0.69
     nhàng
    0.69
     analogs
    0.68
    Activations Density 0.000%

    No Known Activations