© 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. 7997
    Prev
    Next
    INDEX
    Explanations

    AM, age, Axis

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

    The neuron triggers on contact and URL tokens (e.g. domain names, “.com”/slashes, phone‐number or “complete” in form‐fill 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
    ни
    0.87
    ni
    0.81
    拢
    0.79
    ia
    0.79
     enforcement
    0.78
     yg
    0.78
    ول
    0.76
    >"
    0.76
    '
    0.75
    작
    0.73
    POSITIVE LOGITS
     Kõ
    0.93
    muster
    0.93
    nál
    0.86
    калә
    0.86
    ᅱ
    0.84
     sAlarm
    0.82
     sConfig
    0.81
    फोल
    0.81
     Webcam
    0.81
     Least
    0.80
    Activations Density 0.001%

    No Known Activations