© 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. 10-GEMMASCOPE-RES-131K
    7. 105053
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

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

    colons that appear after metadata field names or configuration parameter names in structured data formats.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on numeric tokens (numbers, version strings, or any sequences containing digits).

    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
    },
    -2.36
    }
    -2.13
    });
    -2.05
    _
    -1.87
    ểm
    -1.86
    idemia
    -1.86
    葙
    -1.85
     "..\..\
    -1.83
    　　《
    -1.82
    »,
    -1.80
    POSITIVE LOGITS
    趼
    1.78
    了她
    1.74
     великолеп
    1.72
    𖥧
    1.68
    殽
    1.63
    5
    1.60
    
    1.58
     eléctricas
    1.55
     bele
    1.55
    bufio
    1.55
    Activations Density 0.156%

    No Known Activations