© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9781
    Prev
    Next
    INDEX
    Explanations

    login or logged in

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

    This neuron detects prompts asking the reader to sign in or log in (e.g., “login to view,” “sign in to let us know”).

    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_31_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
    呋
    0.67
    登录
    0.64
     Payment
    0.62
    ulae
    0.59
     இடைய
    0.59
    മ്പര
    0.59
     Immigration
    0.58
    גע
    0.58
    artition
    0.57
    ulating
    0.57
    POSITIVE LOGITS
     oks
    0.58
    声を
    0.53
    Required
    0.52
    required
    0.52
    顕
    0.51
    ecan
    0.51
     scrittura
    0.50
     rischi
    0.50
     dvs
    0.49
    ॉक्स
    0.49
    Activations Density 0.026%

    No Known Activations