© 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. 34-GEMMASCOPE-RES-131K
    7. 98841
    Prev
    Next
    INDEX
    Explanations

    sent date and time in emails

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

    the presence of unusually large numeric tokens (e.g. big numbers in the “Sent:” header) in email metadata.

    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
     мають
    -0.72
     vegetal
    -0.69
     arthur
    -0.67
    Buffer
    -0.66
     ceremonial
    -0.65
    buffer
    -0.65
     emote
    -0.65
    埌
    -0.60
     stimmen
    -0.60
     calend
    -0.60
    POSITIVE LOGITS
     attra
    0.78
    lder
    0.73
     imit
    0.73
    listdir
    0.70
     McN
    0.70
    χν
    0.69
     MCG
    0.69
     öner
    0.68
    dre
    0.68
     deton
    0.68
    Activations Density 0.091%

    No Known Activations