© 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. 8868
    Prev
    Next
    INDEX
    Explanations

    dental problems

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

    The neuron flags section titles or headings (e.g. “Privacy Statement,” “Terms,” “privacy policies”) in formal policy or legal–document text.

    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
    у
    0.80
    ੁ
    0.79
     Untuk
    0.78
    datos
    0.77
    יה
    0.77
     Для
    0.76
    änner
    0.76
    abhavena
    0.76
    '])
    0.75
    Для
    0.75
    POSITIVE LOGITS
    ဖ
    0.72
    ès
    0.67
     accident
    0.65
    。”
    0.65
     Casta
    0.64
    SPC
    0.64
    TSP
    0.64
    ÉS
    0.63
     accents
    0.63
    σία
    0.63
    Activations Density 0.001%

    No Known Activations