© 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. 15379
    Prev
    Next
    INDEX
    Explanations

    goth girls, toy categories, dice rolls

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

    This neuron responds to numeric tokens, especially measurements, quantities, or values (including decimals).

    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
     ボ
    0.90
     スニーカー
    0.84
     Moto
    0.81
     Debido
    0.81
     |,
    0.80
     冖
    0.80
     ミニ
    0.77
     シ
    0.77
     由于
    0.76
     Because
    0.76
    POSITIVE LOGITS
     rundown
    0.68
     expansive
    0.64
    стройки
    0.64
     polished
    0.63
     profound
    0.61
     misc
    0.60
    вшейся
    0.60
     standout
    0.59
     sundry
    0.59
     defunct
    0.58
    Activations Density 0.008%

    No Known Activations