© 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. 8666
    Prev
    Next
    INDEX
    Explanations

    VP returns creating Sport amount

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

    The neuron fires strongly on the very first token of each new text segment (i.e. at the start of a paragraph or block).

    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
     estudos
    0.85
     SUCH
    0.84
    👿
    0.84
    PACK
    0.84
    TION
    0.82
    (//
    0.82
     antimony
    0.81
    इंडियन
    0.81
     hizo
    0.81
    🍠
    0.79
    POSITIVE LOGITS
    cs
    0.75
    ovac
    0.71
    čas
    0.68
    यन
    0.68
     Democratic
    0.67
    ıml
    0.65
    fordert
    0.65
    pause
    0.64
     postponed
    0.64
    ार्थी
    0.64
    Activations Density 0.000%

    No Known Activations