© 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. 10106
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun + person/entity

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

    The neuron is chiefly sensitive to mentions of quantities or ordered items—i.e. numeric or ordinal expressions (e.g. “one+,” “next,” “two,” etc.).

    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
    pca
    0.96
    ת
    0.88
    นาม
    0.77
    pic
    0.75
    про
    0.75
     Hakk
    0.75
    นอน
    0.74
    لود
    0.74
    ਤ
    0.73
    freetype
    0.73
    POSITIVE LOGITS
     aquellos
    0.95
     aquel
    0.89
     aquella
    0.83
     mujeres
    0.83
     opinión
    0.83
     traslad
    0.82
     correctamente
    0.82
     narrativa
    0.82
     podrás
    0.80
     précédents
    0.80
    Activations Density 0.000%

    No Known Activations