© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2097
    Prev
    Next
    INDEX
    Explanations

    place names and brands

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

    This neuron specializes in detecting named entities referring to specific establishments or brand/place names.

    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
    стно
    0.57
    ቝ
    0.57
    iculis
    0.55
    чения
    0.54
    habt
    0.54
    😰
    0.53
    measurable
    0.52
    Histogram
    0.51
    ෲ
    0.51
    listBox
    0.51
    POSITIVE LOGITS
     Damit
    0.58
     confectionery
    0.57
     reimag
    0.55
     King
    0.54
     tätig
    0.54
     Summit
    0.54
     Plaza
    0.53
     santé
    0.53
     brainchild
    0.53
     South
    0.52
    Activations Density 0.020%

    No Known Activations