© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13393
    Prev
    Next
    INDEX
    Explanations

    24/7 availability

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

    The neuron specializes in spotting the “24/7” time-or-service indicator (the digits “24” followed by a slash and “7”).

    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
     it
    -2.14
    </b>
    -1.92
    mahaman
    -1.89
     suitable
    -1.83
     ingenious
    -1.78
     debemos
    -1.78
     idealistic
    -1.78
    mıştır
    -1.77
     tangible
    -1.77
    俳
    -1.77
    POSITIVE LOGITS
     THOSE
    2.16
    </h3>
    1.98
    ⬮
    1.91
     быстро
    1.91
    ate
    1.83
    
    1.78
    ro
    1.77
    数据
    1.76
     BECAUSE
    1.76
    
    1.74
    Activations Density 0.014%

    No Known Activations