© 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. 3777
    Prev
    Next
    INDEX
    Explanations

    over / exceeding a quantity

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

    This neuron detects large numeric values, especially floating-point numbers (e.g. statistical or monetary figures with decimal precision).

    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
    3
    0.68
    around
    0.68
    4
    0.68
    7
    0.68
    6
    0.66
     approximately
    0.65
    5
    0.64
    約
    0.64
    9
    0.63
    AL
    0.61
    POSITIVE LOGITS
     nyata
    0.75
    fach
    0.67
     mogelijkheden
    0.64
     bequem
    0.63
    liefer
    0.60
    nungen
    0.59
     schön
    0.59
     modernen
    0.59
    辦法
    0.57
     masala
    0.57
    Activations Density 0.001%

    No Known Activations