© 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. 4774
    Prev
    Next
    INDEX
    Explanations

    important considerations

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

    The neuron fires on legal/privacy jargon, especially mentions of personal data, “Information,” and related terms in privacy-policy contexts.

    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
    С
    0.82
    ۰
    0.67
    rijke
    0.66
    IPv
    0.66
    א
    0.66
    În
    0.66
    І
    0.65
    Votre
    0.64
     آئی
    0.64
    aceted
    0.64
    POSITIVE LOGITS
     trotzdem
    0.70
     changes
    0.68
     Partai
    0.67
     &/
    0.66
     etc
    0.64
     orada
    0.64
     değişiklik
    0.64
     Changes
    0.64
     ataupun
    0.63
     objections
    0.63
    Activations Density 0.841%

    No Known Activations