© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6553
    Prev
    Next
    INDEX
    Explanations

    equations or code snippets

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

    This neuron fires most strongly on the very first substantive word of a new paragraph or section.

    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
     mélange
    0.86
    皚
    0.74
     للك
    0.73
    ين
    0.71
    ंगली
    0.71
    leiding
    0.70
     attractive
    0.69
     Kre
    0.69
     Geschäfts
    0.69
    wasser
    0.69
    POSITIVE LOGITS
    .",[
    0.82
     irrepar
    0.82
     insuf
    0.77
     అరుణ
    0.75
    য়
    0.73
    Denied
    0.70
     лишь
    0.69
    挕
    0.68
     doğrudan
    0.68
     ১৮
    0.67
    Activations Density 0.000%

    No Known Activations