© 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. 6253
    Prev
    Next
    INDEX
    Explanations

    explains acronyms and technical terms

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

    The neuron strongly lights up on named entities or formal labels—proper nouns, product or project titles, and other multiword “title‐style” phrases.

    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
    3
    0.70
    6
    0.69
    7
    0.68
    2
    0.67
    9
    0.66
    via
    0.66
    8
    0.66
    K
    0.63
    V
    0.63
    t
    0.62
    POSITIVE LOGITS
    というのは
    1.96
    是指
    1.95
     refers
    1.84
     означает
    1.83
    指的是
    1.83
     adalah
    1.77
     అనేది
    1.71
    是一种
    1.68
    是一種
    1.63
     denotes
    1.63
    Activations Density 0.387%

    No Known Activations