© 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. 2262
    Prev
    Next
    INDEX
    Explanations

    online "

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

    This neuron fires most strongly on the vague placeholder word “something” (and similar indefinite pronouns).

    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
     учетом
    0.81
    <bbox>
    0.77
    ழ்பெற்ற
    0.75
    esent
    0.74
    сным
    0.73
     вашей
    0.72
     Faça
    0.72
     бюджета
    0.71
    amanho
    0.71
    escale
    0.70
    POSITIVE LOGITS
    ׂ
    0.84
     adlı
    0.76
    nach
    0.73
    អាច
    0.72
     Plus
    0.71
    成绩
    0.71
    ↵
    0.70
     oan
    0.70
     Bites
    0.69
     Ars
    0.68
    Activations Density 0.000%

    No Known Activations