© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10038
    Prev
    Next
    INDEX
    Explanations

    method capacity

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

    The neuron is looking for numeric tokens or numeric expressions (e.g. measurements, identifiers, or reference numbers).

    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
    тири
    0.79
    ватися
    0.74
     infix
    0.74
    sax
    0.73
     eastbound
    0.73
    developing
    0.72
    s
    0.71
    ORIENTATION
    0.70
    ULTURE
    0.70
    )},\
    0.70
    POSITIVE LOGITS
     Před
    0.74
     berätt
    0.71
    க்கார
    0.67
    raž
    0.66
     getConnection
    0.66
    兩人
    0.66
    ুগত্য
    0.66
     pokrač
    0.65
    rü
    0.65
    文件中
    0.65
    Activations Density 0.001%

    No Known Activations