© 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. 13767
    Prev
    Next
    INDEX
    Explanations

    concealment. presentation. insert. Oracle Fusion

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

    This neuron fires on document section headings or titles (e.g. Wikipedia-style headings).

    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
    ry
    0.85
     avanzados
    0.82
     připoj
    0.80
     sevi
    0.79
    🅔
    0.79
     fáciles
    0.78
    rb
    0.76
     públic
    0.75
     personales
    0.75
     myeloid
    0.75
    POSITIVE LOGITS
     लेने
    0.73
    της
    0.72
     goes
    0.70
     της
    0.70
     हेतु
    0.69
    )--
    0.69
     tentunya
    0.68
    الق
    0.68
    で行
    0.66
    инг
    0.66
    Activations Density 0.000%

    No Known Activations