© 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. 11593
    Prev
    Next
    INDEX
    Explanations

    given names

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

    The neuron is basically a “number‐context” detector—it activates on words appearing right around or adjacent to explicit numeric or quantitative expressions (dates, measurements, counts, 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
     Whitaker
    0.71
    p
    0.68
     Communications
    0.68
     Partnership
    0.66
    ranks
    0.65
     kelamin
    0.65
     بدان
    0.65
     Cooper
    0.64
    ów
    0.63
    </em>
    0.63
    POSITIVE LOGITS
     EtOH
    0.87
    ER
    0.85
     daños
    0.84
    ми
    0.83
     heutigen
    0.82
    ад
    0.79
    jenigen
    0.79
     branche
    0.79
    Hfn
    0.79
    ер
    0.78
    Activations Density 0.000%

    No Known Activations