© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2963
    Prev
    Next
    INDEX
    Explanations

    filler word "like"

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

    The neuron strongly activates on the discourse filler/comparison “Like” (when “Like” begins a clause or sentence).

    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_31_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
     মতো
    0.68
    <h2>
    0.65
     ponieważ
    0.62
    甚至是
    0.60
    只是
    0.59
    であろう
    0.59
    }.}
    0.59
     like
    0.58
    囗
    0.57
    ような
    0.57
    POSITIVE LOGITS
     څنګه
    1.11
     minded
    0.91
     unto
    0.89
     moths
    0.88
     wildfire
    0.86
     folgt
    0.85
    WISE
    0.80
    crazy
    0.79
    minded
    0.75
     vultures
    0.75
    Activations Density 0.202%

    No Known Activations