© 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. 7387
    Prev
    Next
    INDEX
    Explanations

    navigating company processes

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

    The neuron strongly activates on boilerplate legal/disclaimer language (the formal “data protection,” “consent,” “rights,” “contractual”-style clauses), i.e. GDPR‐style regulatory 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
    nak
    0.79
    nih
    0.78
    с
    0.77
    mon
    0.75
    ok
    0.71
    iniz
    0.71
    D
    0.71
    ek
    0.70
    nio
    0.70
     লিপিবদ্ধ
    0.70
    POSITIVE LOGITS
    UAWEI
    0.84
     Fittings
    0.84
     Lemmas
    0.82
    ayakan
    0.80
     atyp
    0.80
    ২৯
    0.79
    MAPb
    0.78
    であろう
    0.78
    ódigo
    0.78
     gegründ
    0.77
    Activations Density 0.001%

    No Known Activations