© 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. 22-GEMMASCOPE-RES-131K
    7. 84281
    Prev
    Next
    INDEX
    Explanations

    let you know how

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

    This neuron fires on speech-act phrases where the speaker directly informs or tells the reader something—e.g. “let you know,” “tell you how…,” “know that….”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     into
    -0.95
    カテ
    -0.92
     учащихся
    -0.90
    nappropriate
    -0.86
    おめでとうございます
    -0.84
     immedi
    -0.84
     previous
    -0.83
     ferroviaire
    -0.82
     secco
    -0.82
    утбо
    -0.82
    POSITIVE LOGITS
     thank
    0.99
     thanks
    0.98
    message
    0.94
     love
    0.93
     their
    0.93
     you
    0.92
    
    0.90
    မ
    0.90
    ane
    0.89
    支持
    0.88
    Activations Density 0.022%

    No Known Activations