© 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. 11156
    Prev
    Next
    INDEX
    Explanations

    guide student, formula, comedian

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

    This neuron is highly sensitive to tokens that appear in section or article headings (e.g. title or “lead‐in” words signaling a new segment).

    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
    
    0.31
    Organisation
    0.31
     ORGANIZATION
    0.31
    женности
    0.30
     organizacji
    0.30
    ULTY
    0.30
     Recently
    0.30
     পাওয়
    0.30
     totalPrice
    0.29
    requently
    0.29
    POSITIVE LOGITS
     spectral
    0.30
    用
    0.29
     myself
    0.29
    のお
    0.29
     に
    0.28
     foc
    0.28
     jej
    0.27
     devo
    0.27
     zou
    0.27
    之
    0.27
    Activations Density 0.000%

    No Known Activations