© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11352
    Prev
    Next
    INDEX
    Explanations

    true or false

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

    This neuron responds to numbers or numeric parameter tokens (e.g. digit sequences and values in URLs or key-value flags).

    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_31_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
    ≒
    0.70
     =-
    0.69
    Cleaner
    0.66
    =-
    0.66
    emale
    0.66
    Constr
    0.64
    =-\
    0.64
    =(-
    0.64
    大约
    0.63
    resher
    0.63
    POSITIVE LOGITS
     true
    1.16
     false
    1.00
    false
    0.87
    true
    0.85
     yes
    0.67
     UK
    0.64
     NONE
    0.64
     tragic
    0.62
     verdadeira
    0.62
     none
    0.61
    Activations Density 0.026%

    No Known Activations