© 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. 5926
    Prev
    Next
    INDEX
    Explanations

    Focus, Strengths, Revenue, Impact, Benefits, Style

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

    The neuron activates on section heading labels or “signpost” phrases (e.g. “Tools to Use,” “Case Study,” “Challenge,” “Solution,” “Competitive Advantage,” etc.).

    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
     accountNumber
    0.56
     }//
    0.55
     glioma
    0.55
     "]");
    0.54
     discretization
    0.54
    psr
    0.54
     เป
    0.53
     subscript
    0.53
    ุ
    0.53
     ()=>{
    0.52
    POSITIVE LOGITS
    ‌ها
    0.65
    même
    0.58
     mêmes
    0.57
     Beaucoup
    0.57
    Dieses
    0.55
     Même
    0.55
    Numerous
    0.55
    ‌هایی
    0.53
    Questo
    0.53
    International
    0.53
    Activations Density 0.005%

    No Known Activations