© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84501
    Prev
    Next
    INDEX
    Explanations

    structure-defining punctuation

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

    The neuron activates on numeric literal tokens in code (i.e. numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     '')
    -1.45
    )
    -1.36
    ())
    -1.22
    )
    -1.16
    ")
    -1.15
    .)
    -1.13
     "")
    -1.13
    )$
    -1.09
     _)
    -1.09
     .)
    -1.06
    POSITIVE LOGITS
     };
    1.09
     },
    1.04
    },
    0.97
    ","","
    0.95
     */,
    0.95
     }},
    0.90
     });
    0.88
     };
    0.86
     }.
    0.84
    Бележки
    0.82
    Activations Density 0.008%

    No Known Activations