© 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. 19450
    Prev
    Next
    INDEX
    Explanations

    six followed by related words

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

    The neuron activates specifically on occurrences of the number “six” (either spelled out or as a token).

    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
    ↵↵
    -4.59
     
    -4.50
    1
    -3.56
    the
    -3.27
    S
    -2.97
    “
    -2.94
    E
    -2.91
    ”
    -2.81
    A
    -2.64
      
    -2.59
    POSITIVE LOGITS
    dijual
    2.98
    ?"
    2.88
    𝗲
    2.83
    ！"
    2.83
    鏖
    2.81
    蕷
    2.78
    ፝
    2.73
    }$
    2.72
    埸
    2.72
    ipzig
    2.70
    Activations Density 0.016%

    No Known Activations