© 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. 253
    Prev
    Next
    INDEX
    Explanations

    if your

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

    The neuron specializes in detecting subordinating conjunctions and contrast markers (e.g. “if,” “even,” “though,” “when,” “despite,” “while”) that introduce conditional or concessive clauses.

    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
    0.24
    '
    0.23
    ()
    0.22
     ()
    0.22
    ></
    0.22
    -
    0.22
    ↵↵
    0.21
    _
    0.21
             
    0.21
     */
    0.21
    POSITIVE LOGITS
    you
    0.42
     તમે
    0.38
     شما
    0.38
     आप
    0.36
     you
    0.35
     youre
    0.35
     jūs
    0.35
     você
    0.34
     আপনি
    0.34
    你不
    0.33
    Activations Density 0.554%

    No Known Activations