© 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. 9763
    Prev
    Next
    INDEX
    Explanations

    sentence boundary transition

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

    The neuron fires most strongly on numeric specifications and measurements (e.g. values with units).

    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
     hiszen
    0.75
    🤎
    0.72
     sogen
    0.72
    💫
    0.71
    🤜
    0.71
    🧚
    0.69
     WHICH
    0.67
     Undoubtedly
    0.67
    wherein
    0.66
    💛
    0.66
    POSITIVE LOGITS
    <unused2200>
    0.64
     d
    0.61
     работают
    0.59
     velocities
    0.57
     system
    0.55
     contient
    0.54
     działa
    0.54
     funcionan
    0.54
     salic
    0.53
     Πε
    0.53
    Activations Density 0.473%

    No Known Activations