© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12193
    Prev
    Next
    INDEX
    Explanations

    session mode or manager

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

    The neuron fires on mentions of web‐analytics tracking (especially “cookies,” “session(s),” and related terms).

    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
    beds
    0.60
     Beds
    0.56
    บคุม
    0.55
    벗
    0.55
     né
    0.54
    鸨
    0.54
    🔩
    0.54
    ין
    0.54
    👷
    0.54
     Gron
    0.53
    POSITIVE LOGITS
     Session
    2.23
     session
    2.14
    Session
    2.02
     SESSION
    2.02
    session
    1.95
    SESSION
    1.94
     Sessions
    1.93
     sess
    1.92
     sessions
    1.86
    Sessions
    1.82
    Activations Density 0.071%

    No Known Activations