© 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. 296
    Prev
    Next
    INDEX
    Explanations

    seven

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

    The neuron fires on multi‐digit numeric tokens (i.e. large numbers rather than single 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_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
     regretted
    -0.80
    getFirstName
    -0.79
    
    -0.78
    
    -0.77
    lihood
    -0.75
    𝟖
    -0.75
    يلة
    -0.75
    formatics
    -0.73
    didReceive
    -0.72
    寶寶
    -0.71
    POSITIVE LOGITS
    7
    3.06
     seven
    2.95
     seventh
    2.31
     Seven
    2.31
    七
    2.14
     Seventh
    2.09
    Seven
    2.08
    ⑦
    2.06
     SEVEN
    2.03
    ７
    1.98
    Activations Density 0.133%

    No Known Activations