© 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. 5915
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily activates on numeric tokens (numbers and digits) in the text.

    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
    })-(\
    0.66
    }}-\
    0.65
    )/(
    0.58
    }}=(
    0.57
    )-\
    0.57
     evaporating
    0.57
    })-\
    0.55
     \
    0.54
    })+\
    0.53
     complementary
    0.53
    POSITIVE LOGITS
    +
    1.20
    ＋
    1.07
    +.
    1.06
     $+
    1.03
    +:
    0.91
    $+
    0.90
    +,
    0.89
     +
    0.81
    +//
    0.77
    +]
    0.77
    Activations Density 0.019%

    No Known Activations