© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1944
    Prev
    Next
    INDEX
    Explanations

    master of a craft

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

    This neuron fires on numeric expressions (years, quantities, monetary amounts, and other number 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_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
    那样
    0.72
     того
    0.69
    That
    0.65
    としては
    0.64
    them
    0.64
     другую
    0.64
    :
    0.64
    那个
    0.63
     அவனை
    0.62
     THEM
    0.62
    POSITIVE LOGITS
     this
    1.13
     youll
    1.09
     we
    0.99
     you
    0.98
     it
    0.96
     there
    0.95
     یہ
    0.95
     यह
    0.91
     these
    0.90
     questa
    0.90
    Activations Density 0.258%

    No Known Activations