© 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. 14834
    Prev
    Next
    INDEX
    Explanations

    forms, roles, New, weather, Nov, efficient, random

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

    The neuron flags the first substantive (non–stop) content word that appears at the start of each new 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
    𝚏
    0.96
    𝚐
    0.92
    𝚝
    0.91
     осіб
    0.89
     Ironically
    0.89
    𝚊
    0.89
     інте
    0.88
     ഒരാ
    0.87
    壃
    0.86
    fixing
    0.86
    POSITIVE LOGITS
    nik
    0.69
    ler
    0.64
     rely
    0.64
     mature
    0.64
     predefined
    0.63
     stratified
    0.61
     brute
    0.61
    lar
    0.59
     lose
    0.59
    schemaLocation
    0.59
    Activations Density 0.000%

    No Known Activations