© 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. 2983
    Prev
    Next
    INDEX
    Explanations

    country abbreviations and specific terms

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

    The neuron flags tokens that appear in privacy‐policy or legal/disclaimer subsections—e.g. terms around data protection (GDPR), mailing-list management (footer, email, unsubscribe, newsletters), and related compliance jargon.

    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
    did
    0.78
    虔
    0.78
    Ἥ
    0.70
    ➡
    0.70
    Did
    0.70
    pointB
    0.70
    মুসলিম
    0.70
    టీ
    0.68
    ریع
    0.68
    setUsername
    0.68
    POSITIVE LOGITS
     WWW
    0.74
    i
    0.72
    u
    0.71
     analogues
    0.70
     tanha
    0.69
     refined
    0.68
     предоставля
    0.68
     dodge
    0.68
     analogous
    0.68
     hectares
    0.67
    Activations Density 0.061%

    No Known Activations