© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14704
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    The neuron is specialized to detect personal names (proper-name tokens).

    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
     (
    0.66
    áte
    0.63
     तिक
    0.62
     në
    0.61
     openings
    0.61
     현재
    0.61
     Authorities
    0.61
     titers
    0.61
     ("
    0.61
     (=
    0.61
    POSITIVE LOGITS
    这样一个
    0.67
    STRAINT
    0.67
     retiro
    0.58
    hwar
    0.58
    ുകയായിരുന്നു
    0.56
    នុស្ស
    0.56
     desayuno
    0.55
    這樣子
    0.55
    每个人
    0.55
     suelo
    0.54
    Activations Density 0.005%

    No Known Activations