© 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. 10343
    Prev
    Next
    INDEX
    Explanations

    dimensions (length, width, height)

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

    The neuron is essentially signaling when it’s seeing the first content word of a sentence (i.e. sentence-initial tokens).

    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
    Under
    0.81
    SL
    0.78
    Nya
    0.77
     Unter
    0.77
    𝘦
    0.77
    Gu
    0.76
    Wise
    0.76
    SS
    0.75
    Sw
    0.74
     Facing
    0.74
    POSITIVE LOGITS
     nucleons
    0.96
    ມັນ
    0.95
     핵
    0.86
     clams
    0.84
    獗
    0.84
     smelting
    0.84
    ડિયા
    0.82
     bushings
    0.82
     samano
    0.81
     calcite
    0.80
    Activations Density 0.000%

    No Known Activations