© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10512
    Prev
    Next
    INDEX
    Explanations

    letter, story, note, list

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

    The neuron responds strongly to nouns naming scheduled or organized events and professional engagements (e.g. interview, consultation, appointment, tour, trip, visit).

    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
    ள்
    0.68
    ات
    0.66
    ב
    0.65
    际
    0.63
    춰
    0.63
    ಷ
    0.62
     clues
    0.62
    клады
    0.61
     reputations
    0.61
    队伍
    0.60
    POSITIVE LOGITS
     sagt
    0.80
    ❤️❤️
    0.74
     Zellen
    0.73
    .\\
    0.73
     beträgt
    0.72
     tratto
    0.71
     baseado
    0.71
     betont
    0.70
     schreibt
    0.70
     sells
    0.69
    Activations Density 0.658%

    No Known Activations