© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5818
    Prev
    Next
    INDEX
    Explanations

    personal, individualized, organization

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

    The neuron fires on temporal or quantitative cue words (e.g. “daily,” “time,” “under,” “late”) that introduce measures of duration, age, frequency, or penalties.

    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
     batalha
    0.89
    令牌
    0.88
    しかし
    0.88
    硗
    0.87
     最初
    0.86
    噻
    0.86
    जेदार
    0.82
    ートン
    0.80
    ピンク
    0.80
    再生
    0.80
    POSITIVE LOGITS
    ness
    0.75
    ди
    0.72
    ]
    0.69
    bred
    0.69
    ]`
    0.67
    )}}{\
    0.65
     svare
    0.65
     Wet
    0.63
     atheist
    0.63
    b
    0.63
    Activations Density 0.000%

    No Known Activations