© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5661
    Prev
    Next
    INDEX
    Explanations

    listing items in text

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

    This neuron detects section-heading labels (e.g. “Design,” “Methodology,” “Purpose,” “Objectives”) that mark structural divisions in academic papers.

    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
    s
    1.03
    t
    0.80
     reprodu
    0.77
    िंग
    0.76
     trat
    0.76
     TAR
    0.76
    ING
    0.76
    علي
    0.75
    Y
    0.74
     pomeriggio
    0.73
    POSITIVE LOGITS
     Abroad
    0.85
    🗸
    0.73
     Classics
    0.73
     त्याच्या
    0.73
    Abroad
    0.73
     जाकर
    0.71
    起到
    0.70
     Drawing
    0.70
     প্রাস
    0.69
     Diffusion
    0.69
    Activations Density 0.000%

    No Known Activations