© 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. 13183
    Prev
    Next
    INDEX
    Explanations

    types of databases, lenses, cooking pans

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

    The neuron detects specific product- or brand-related nouns (e.g. names of goods, companies, or item categories).

    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
    е
    0.87
    umble
    0.79
    awatir
    0.76
     aprire
    0.76
    endra
    0.74
    Accelerometer
    0.74
     informazioni
    0.74
    𝚊
    0.73
     வீடியோ
    0.72
    fadeIn
    0.72
    POSITIVE LOGITS
     ministers
    0.88
     CREAM
    0.85
     nominees
    0.83
    จาก
    0.77
     patriots
    0.76
     γεν
    0.75
     patrón
    0.75
     Archdiocese
    0.74
     featuring
    0.73
    μος
    0.72
    Activations Density 2.146%

    No Known Activations