© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6300
    Prev
    Next
    INDEX
    Explanations

    bag contents

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

    The neuron predominantly activates on numeric tokens (e.g. years, quantities, percentages).

    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_31_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
    I
    0.73
    En
    0.73
    Im
    0.72
    Don
    0.72
    An
    0.71
    L
    0.71
    American
    0.70
    C
    0.70
    A
    0.70
    No
    0.68
    POSITIVE LOGITS
     shinobi
    0.64
     bytecode
    0.62
     SalesLT
    0.61
     NodeType
    0.60
     MetaMask
    0.59
     Async
    0.59
     auf
    0.57
     deviceInfo
    0.57
     workaround
    0.57
     fallback
    0.57
    Activations Density 0.172%

    No Known Activations