© 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. 11430
    Prev
    Next
    INDEX
    Explanations

    code examples and descriptions

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

    The neuron fires on verbs and phrases that express obtaining, requesting, or looking for something (e.g. “collect,” “looking for,” “obtained”).

    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
    o
    0.94
    l
    0.94
    ל
    0.90
    liz
    0.89
    م
    0.88
    rne
    0.87
    rn
    0.86
    ar
    0.85
    me
    0.85
    por
    0.85
    POSITIVE LOGITS
    вица
    0.80
     romaine
    0.78
     CHAS
    0.77
    логия
    0.76
    鬍
    0.76
    .`);
    0.75
     ALE
    0.75
     NIO
    0.74
     МА
    0.74
    ச்சி
    0.74
    Activations Density 0.000%

    No Known Activations