© 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. 1904
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric tokens—years, quantities, statistics, and other number-like values.

    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
    ”
    0.94
    」
    0.88
    ")
    0.86
    (".")
    0.84
    "
    0.84
    "?>
    0.84
    )
    0.79
    "]="
    0.77
    :")
    0.76
    }
    0.73
    POSITIVE LOGITS
    (),
    2.95
    】,
    2.92
     '',
    2.91
     [],
    2.91
     "",
    2.86
    !,
    2.86
    `,
    2.80
    ?,
    2.80
     {},
    2.75
    '',
    2.75
    Activations Density 0.578%

    No Known Activations