© 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. 1338
    Prev
    Next
    INDEX
    Explanations

    attaching files to emails

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

    The neuron fires on code tokens involved in attaching files to an email (e.g. attachment, attach, filename, open, email, MIME, add_header).

    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
    cierge
    -0.81
    乏
    -0.71
    ímetros
    -0.71
    getti
    -0.69
     circles
    -0.69
    postValue
    -0.69
     लिख
    -0.68
    出版年
    -0.66
    ubro
    -0.66
    elb
    -0.65
    POSITIVE LOGITS
     attachments
    5.53
     attachment
    5.47
    Attachment
    4.53
    attachment
    4.50
     Attachment
    4.31
     Attachments
    4.19
    attachments
    4.16
    Attachments
    4.06
     attached
    3.89
     attach
    3.72
    Activations Density 0.097%

    No Known Activations