© 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. 14232
    Prev
    Next
    INDEX
    Explanations

    is a

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

    This neuron strongly activates on the first meaningful word at the start of a new sentence or line.

    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
     فرص
    0.81
    ities
    0.78
     Program
    0.74
    ൾ
    0.74
     नरम
    0.73
     потря
    0.72
    ما
    0.71
    heroku
    0.71
     Videos
    0.71
    jut
    0.71
    POSITIVE LOGITS
    㻁
    0.85
     situés
    0.81
     gravi
    0.79
    𝑚
    0.74
     câble
    0.73
     ciências
    0.72
     située
    0.71
    态
    0.71
    ₀
    0.71
    忡
    0.71
    Activations Density 0.001%

    No Known Activations