© 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. 6076
    Prev
    Next
    INDEX
    Explanations

    Spanish words

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

    The neuron lights up on relatively uncommon, content-bearing words (e.g. non-stopwords) rather than on high-frequency function words.

    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
    व
    0.82
    л
    0.78
    ма
    0.75
    ного
    0.75
     -
    0.74
    кови
    0.71
    Obviously
    0.70
    <0x80>
    0.70
    ী
    0.70
    ссе
    0.67
    POSITIVE LOGITS
     Más
    0.96
     cuáles
    0.88
    厛
    0.88
     potenci
    0.86
     vál
    0.86
     Ahí
    0.85
     andar
    0.83
    芴
    0.81
     каттоо
    0.80
     inscripción
    0.80
    Activations Density 0.001%

    No Known Activations