© 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. 10624
    Prev
    Next
    INDEX
    Explanations

    incals, wishes for, appropriate boundaries, controlled policy

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

    This neuron consistently fires on words appearing at the start of segments or sentences (i.e. tokens in sentence-initial position).

    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
    michael
    0.66
    king
    0.66
    op
    0.64
     
    0.64
    and
    0.63
    son
    0.63
     dollars
    0.63
     R
    0.61
    était
    0.60
     dummy
    0.59
    POSITIVE LOGITS
     Freeport
    0.99
     सीबीआई
    0.95
    hattim
    0.92
     equipado
    0.91
    تي
    0.89
     воору
    0.89
     ون
    0.88
    পক্ষে
    0.88
     diferença
    0.87
     Veränder
    0.87
    Activations Density 0.000%

    No Known Activations