© 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. 34-GEMMASCOPE-RES-131K
    7. 116316
    Prev
    Next
    INDEX
    Explanations

    send/sent

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

    The neuron is detecting self‐references or first‐person agency terms (e.g. “I,” “self,” “you,” “someone,” “sent,” “has attempted,” etc.).

    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
     Şubat
    -0.83
    hla
    -0.80
    𝚞
    -0.75
    ☎️
    -0.75
    ibus
    -0.74
    读者
    -0.70
    쉘
    -0.70
    Geschiedenis
    -0.68
    ensaft
    -0.67
    ographi
    -0.66
    POSITIVE LOGITS
     send
    6.13
     sending
    5.78
     sent
    5.47
     sends
    5.44
     Send
    4.91
    send
    4.88
    Send
    4.88
    发送
    4.41
    Sending
    4.34
     Sending
    4.31
    Activations Density 0.226%

    No Known Activations