© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127710
    Prev
    Next
    INDEX
    Explanations

    countries, companies, and cities in lists

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

    The neuron consistently fires on the labels or “item” names in data‐value pairs (the category tokens that appear just before numeric measurements in tables or lists).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     also
    -1.71
     from
    -1.40
     on
    -1.34
     también
    -1.30
    靭
    -1.26
     serta
    -1.21
     ensuite
    -1.19
     ALSO
    -1.15
     også
    -1.14
    就
    -1.13
    POSITIVE LOGITS
     évidemment
    1.15
    给了
    1.13
     durabilidad
    1.08
     существует
    1.07
     dacă
    1.07
    </tbody>
    1.06
     niemals
    1.04
     that
    1.03
    </h3>
    1.02
     vanil
    1.02
    Activations Density 0.546%

    No Known Activations