© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 31
    Prev
    Next
    INDEX
    Explanations

    This neuron detects numeric literal values (e.g. numbers following keys or in code).

    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
     ऑगस्ट
    0.58
    établissement
    0.57
     सप्टेंबर
    0.55
    aluminum
    0.55
     आरमार
    0.55
     ciertos
    0.54
    symplectic
    0.53
    ॕ
    0.53
    skyscraper
    0.53
    trombone
    0.53
    POSITIVE LOGITS
     }
    1.20
     },
    0.95
     };
    0.87
     }}
    0.87
     })
    0.84
     }.
    0.82
     )}
    0.82
    }
    0.80
     });
    0.80
     }//
    0.78
    Activations Density 0.002%

    No Known Activations