© 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. 384
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric expressions—especially floating-point numbers with decimals.

    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
    !).
    0.44
    %).
    0.43
    ”。
    0.43
    。
    0.42
    だったので
    0.42
    homotopic
    0.41
    特别
    0.40
    ዋል።
    0.39
    )$.
    0.39
    ですので
    0.39
    POSITIVE LOGITS
     ،
    0.63
     there
    0.59
     ,
    0.55
     thì
    0.53
     ，
    0.53
    ,__
    0.51
     may
    0.50
    ，《
    0.49
    ,’
    0.49
     ,\
    0.49
    Activations Density 0.000%

    No Known Activations