© 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. 2840
    Prev
    Next
    INDEX
    Explanations

    validation and description

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

    The neuron specializes in spotting formal legal and procedural terminology—words describing steps, actions, and assessments in a judicial investigation or court proceeding.

    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
    utiérrez
    0.93
     দুর্দান্ত
    0.93
    ᑉ
    0.93
    Precio
    0.90
     descobrir
    0.88
    ើញ
    0.88
    rieron
    0.88
     આમંત્રણ
    0.87
    ᕆ
    0.87
     ভালোবাস
    0.86
    POSITIVE LOGITS
     upto
    1.40
     of
    1.31
     aforesaid
    1.28
     bhi
    1.16
     equipments
    1.06
    /
    1.04
     pursuance
    1.03
     same
    1.02
     kuchh
    1.02
     S
    1.01
    Activations Density 0.031%

    No Known Activations