© 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. 12587
    Prev
    Next
    INDEX
    Explanations

    specific areas, greener, absolute, conceptual, specify colons

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

    The neuron fires strongly on the first salient (non‐zero) content word at the start of each text 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
     dikdört
    0.87
     вый
    0.83
     некоторы
    0.82
     продолжа
    0.81
    땄
    0.80
     sekund
    0.80
    仨
    0.79
    руют
    0.78
     один
    0.78
     столько
    0.77
    POSITIVE LOGITS
    ’
    0.89
    '
    0.76
    ０
    0.75
    The
    0.74
    ဆေး
    0.71
    This
    0.68
     Specifically
    0.68
     specifically
    0.67
    ري
    0.67
     stimulate
    0.66
    Activations Density 0.000%

    No Known Activations