© 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. 16097
    Prev
    Next
    INDEX
    Explanations

    imports

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

    The neuron fires on formal policy‐style terms denoting user roles and service entities (e.g. “Users,” “Teacher,” “courses,” “learning,” “service,” “assigned,” “attain,” “We”).

    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
     grueso
    1.00
    Ⲣ
    0.96
    णसी
    0.91
     rodean
    0.86
     compuesto
    0.83
    setImageResource
    0.82
    reflectionMap
    0.81
    renderCamera
    0.81
    ᧐
    0.78
    ০
    0.77
    POSITIVE LOGITS
    c
    0.98
    I
    0.97
        
    0.85
    ა
    0.84
    boks
    0.82
    A
    0.81
    r
    0.81
    it
    0.80
     Announcement
    0.78
     発
    0.77
    Activations Density 2.105%

    No Known Activations