© 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. 3148
    Prev
    Next
    INDEX
    Explanations

    table headers

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

    The neuron specifically detects numeric tokens that include a decimal point (i.e., floating-point numbers).

    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
     }
    0.77
     }{
    0.68
     }[
    0.64
    express
    0.63
     }(
    0.62
     }</
    0.62
    容易
    0.60
     }(\
    0.60
    }[
    0.59
    }{(
    0.59
    POSITIVE LOGITS
    <tr>
    0.98
    </tbody>
    0.96
    </thead>
    0.90
    </tfoot>
    0.75
     ROW
    0.71
     rowing
    0.71
     row
    0.66
     Rowing
    0.63
     ترس
    0.63
     Consejo
    0.63
    Activations Density 0.002%

    No Known Activations