© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72358
    Prev
    Next
    INDEX
    Explanations

    emails, communications, and notes

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

    The neuron activates on words naming communication channels or document/source types (e.g. “comm,” “email,” “Communication,” “interview,” “report”).

    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
    tronlink
    -1.61
    IAC
    -1.47
    
    -1.45
    趿
    -1.43
     normaal
    -1.38
     BATTERY
    -1.38
    ialak
    -1.35
    哙
    -1.34
    KOV
    -1.33
    pelo
    -1.32
    POSITIVE LOGITS
     additional
    1.66
    5
    1.48
     there
    1.47
    3
    1.40
     Ultimately
    1.40
     Surprisingly
    1.39
     after
    1.39
     Interestingly
    1.38
    Surprisingly
    1.38
     people
    1.38
    Activations Density 0.007%

    No Known Activations