© 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. 15572
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronoun "this" in multiple languages

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

    The neuron detects high‐level section headers or titles (e.g. “Responsibilities:”, “Qualifications & Requirements:”, “Role:”) that structure job‐description text.

    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
    <u>
    0.68
    0.68
    <sup>
    0.64
     UT
    0.60
    Department
    0.55
    circa
    0.55
     U
    0.55
    <i>
    0.54
     ${
    0.54
     (
    0.53
    POSITIVE LOGITS
    éseket
    0.66
    твра
    0.65
     astrocyte
    0.64
    ⦁
    0.63
     BlogPost
    0.63
    бро
    0.61
     endif
    0.60
    grat
    0.59
     комплекса
    0.59
    наче
    0.58
    Activations Density 0.010%

    No Known Activations