© 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. 10441
    Prev
    Next
    INDEX
    Explanations

    languages

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

    The neuron fires on structural document markers—terms that denote headings, list items, section numbers, or other layout indicators.

    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
     glyph
    0.86
     ALS
    0.82
     μ
    0.82
     ICP
    0.82
     Nip
    0.80
     Novi
    0.79
     IOP
    0.79
     UTI
    0.75
     ICE
    0.74
     アル
    0.73
    POSITIVE LOGITS
    Բ
    0.94
    }=\
    0.92
     miejsca
    0.90
     distribusi
    0.88
     njihov
    0.87
     memutuskan
    0.86
     kesalahan
    0.82
    っていました
    0.81
     keterampilan
    0.81
    ỏng
    0.80
    Activations Density 0.000%

    No Known Activations