© 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. 15420
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis followed by list items

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

    This neuron strongly fires on uppercase initialisms and acronyms (e.g. EMI, PET, FDG, FACIT-Sp12), i.e. sequences of all-caps letters (often representing technical terms or scales).

    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
    l
    1.08
     sebagainya
    0.96
    k
    0.95
    (!
    0.93
    c
    0.92
    m
    0.90
    r
    0.89
     ardından
    0.88
    j
    0.88
     deth
    0.85
    POSITIVE LOGITS
    你有
    0.96
    有两种
    0.81
    ১২
    0.78
    河流
    0.75
    卓越
    0.75
     lineages
    0.74
    ፦
    0.74
    აღ
    0.74
    壶
    0.74
     क्षेत्रों
    0.73
    Activations Density 0.098%

    No Known Activations