© 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. 7470
    Prev
    Next
    INDEX
    Explanations

    interest and accrual

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

    The neuron detects mentions of personal data handling and privacy‐compliance terms (e.g. disclosure, consent, use of personal information).

    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
    0.74
     estou
    0.67
    战场
    0.67
     dist
    0.64
     mastic
    0.64
     и
    0.63
    现在
    0.63
     dış
    0.63
     ekst
    0.63
     ও
    0.63
    POSITIVE LOGITS
     ។
    0.72
     対象
    0.72
     같아요
    0.68
    úde
    0.67
     있어요
    0.67
     ดัง
    0.66
     ประเภท
    0.66
    «.
    0.66
     AppComponent
    0.65
    ។
    0.65
    Activations Density 0.049%

    No Known Activations