© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8131
    Prev
    Next
    INDEX
    Explanations

    disclaimers or cautionary notes

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

    The neuron detects boilerplate editorial/meta text such as update notices, bylines, “excerpt” labels, and similar article‐level metadata phrases.

    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
    】
    1.20
    】，
    1.19
    ！】
    1.18
    </h3>
    1.16
     】
    1.16
    】,
    1.10
    ']}
    1.08
    ']
    0.96
    】.
    0.96
     】,
    0.95
    POSITIVE LOGITS
    </em>
    1.84
    </i>
    1.69
    );*/
    1.09
    ");*/
    1.02
    
    1.02
    ...*/
    0.97
     */
    0.93
    ;*/
    0.89
    }*/
    0.88
     }*/
    0.88
    Activations Density 0.078%

    No Known Activations