© 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. 72735
    Prev
    Next
    INDEX
    Explanations

    stay tuned for future updates

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

    The neuron fires on “stay tuned” (and similar “keep you posted”) calls to action announcing upcoming content or updates.

    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
    戗
    -1.81
    
    -1.76
    镠
    -1.73
    otriva
    -1.68
    ⚋
    -1.66
    笺
    -1.66
     messo
    -1.63
     sentito
    -1.63
     смотреть
    -1.63
     chiesto
    -1.59
    POSITIVE LOGITS
    '
    2.52
    ll
    2.17
    ,”
    2.00
    ."
    1.93
     '
    1.91
    it
    1.83
    or
    1.75
    </strong>
    1.64
    ot
    1.63
    v
    1.63
    Activations Density 0.004%

    No Known Activations