© 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. 5764
    Prev
    Next
    INDEX
    Explanations

    table, model, matrix

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

    The neuron detects mentions of numeric measurements (especially distances or time spans) often paired with units like “km,” “mile(s),” or “minute(s).”

    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
    }]=
    0.77
    所有的
    0.74
     xrange
    0.71
    StringBuffer
    0.71
    desIP
    0.70
    単純
    0.70
    =='
    0.68
    全て
    0.68
    })=
    0.67
    avgsalary
    0.67
    POSITIVE LOGITS
     DeFi
    1.45
     PFAS
    1.39
     TikTok
    1.34
     metaverse
    1.30
     onboarding
    1.28
     ২০২২
    1.21
     LGBTQ
    1.20
     macOS
    1.20
     fintech
    1.20
     Metaverse
    1.20
    Activations Density 0.012%

    No Known Activations