© 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. 9432
    Prev
    Next
    INDEX
    Explanations

    potential or future outcomes

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

    The neuron strongly activates on emphasis markers—discourse adverbs and intensifiers (e.g. “most,” “importantly,” “indeed,” “no”) that signal or reinforce key points.

    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
    However
    0.83
    Namun
    0.82
    거나
    0.76
    <0xE0>
    0.75
    Pero
    0.73
    however
    0.71
    这时
    0.70
    Entonces
    0.66
    或者是
    0.66
    <0xEF>
    0.65
    POSITIVE LOGITS
     یې
    0.84
     importantly
    0.80
     kreeg
    0.78
     pediu
    0.78
     myös
    0.77
     của
    0.76
     oferece
    0.75
     alltid
    0.74
     compartió
    0.74
     își
    0.73
    Activations Density 0.334%

    No Known Activations