© 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. 7121
    Prev
    Next
    INDEX
    Explanations

    language conjunctions and suffixes

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

    The neuron fires on tokens that contain numbers (i.e. numeric identifiers or abbreviations such as “401(k)” or “Ph.D.”).

    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
    ين
    0.70
    ot
    0.70
    k
    0.63
    el
    0.59
    et
    0.58
    ن
    0.57
    M
    0.57
    T
    0.56
    n
    0.55
    م
    0.55
    POSITIVE LOGITS
    এবং
    0.60
    节日
    0.58
    और
    0.57
    やつ
    0.57
     và
    0.57
     וה
    0.55
    महिला
    0.54
    மைக்
    0.52
    และ
    0.51
     ਅਤੇ
    0.51
    Activations Density 0.000%

    No Known Activations