© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3472
    Prev
    Next
    INDEX
    Explanations

    not only

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

    The neuron strongly activates on the discourse marker “Not only,” i.e. the phrase “Not only” at the start of a clause.

    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
     nascent
    0.66
     happenings
    0.64
    -
    0.60
    plications
    0.59
    _
    0.59
    asted
    0.58
    iliation
    0.58
    ulations
    0.57
     September
    0.55
     Covid
    0.55
    POSITIVE LOGITS
    ل
    0.92
     вам
    0.88
     можете
    0.82
    ו
    0.80
     můžete
    0.78
    ط
    0.78
    ان
    0.77
    你
    0.77
    у
    0.77
    ти
    0.75
    Activations Density 0.013%

    No Known Activations