© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7520
    Prev
    Next
    INDEX
    Explanations

    accounting metrics, coffee cup, scientific data

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

    The neuron fires on promotional verbs and phrases that describe what a place “offers,” “provides,” or otherwise features as amenities or services.

    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
    挫
    0.80
    ሑ
    0.78
     Palmyra
    0.77
     lieve
    0.73
     Ausstellung
    0.72
    ̉i
    0.72
     probabilmente
    0.71
     Enforcement
    0.70
    ْل
    0.70
    克服
    0.70
    POSITIVE LOGITS
     مدت
    0.76
     annum
    0.72
     அதிசயம்
    0.71
    🛌
    0.71
     мощность
    0.70
    с
    0.70
     коэффициент
    0.67
    じゃ
    0.67
     диа
    0.66
     нач
    0.66
    Activations Density 0.000%

    No Known Activations