© 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. 13080
    Prev
    Next
    INDEX
    Explanations

    large language models

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

    The neuron fires strongly on uppercase abbreviations, acronyms, and other all‐caps or technical 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_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
    aquin
    0.88
    ỏa
    0.86
    ి
    0.86
    ocolate
    0.82
    pecial
    0.81
    د
    0.81
    㸮
    0.81
    ঙ্গার
    0.80
    ে
    0.79
     séjour
    0.78
    POSITIVE LOGITS
     LEVEL
    0.77
     Kwa
    0.74
     purporting
    0.70
     Minder
    0.69
     VAN
    0.67
     LANGUAGE
    0.67
     LEON
    0.66
     Yeah
    0.65
     Après
    0.65
     było
    0.65
    Activations Density 0.000%

    No Known Activations