© 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. 1023
    Prev
    Next
    INDEX
    Explanations

    coordinate, bind, wearing, anticipate

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

    The neuron is specifically detecting double-quote characters (i.e. quotation marks).

    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
    ᅬ
    0.87
     Fertil
    0.84
    на
    0.83
    perluan
    0.83
     Це
    0.82
    дна
    0.80
    a
    0.80
    šću
    0.79
     Уже
    0.79
    hya
    0.77
    POSITIVE LOGITS
    ன்
    0.72
    uelle
    0.68
    tok
    0.67
    err
    0.66
    erv
    0.65
     von
    0.65
    ties
    0.64
    塙
    0.63
     islands
    0.61
     النهار
    0.61
    Activations Density 0.001%

    No Known Activations