© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14699
    Prev
    Next
    INDEX
    Explanations

    GameObject node

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

    This neuron fires strongly on the very first substantive word that begins a new sentence or 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
     WATTS
    0.80
     ORNL
    0.79
    EAR
    0.79
    𝘧
    0.79
     ERISA
    0.78
     Shreveport
    0.77
    هُ
    0.75
     sideways
    0.75
     Evam
    0.75
    ॉर्क
    0.75
    POSITIVE LOGITS
    uma
    0.89
    ura
    0.82
    ec
    0.81
    ına
    0.81
    als
    0.77
    aza
    0.76
    থেষ্ট
    0.76
    inin
    0.75
    :");
    0.75
     представ
    0.75
    Activations Density 0.000%

    No Known Activations