© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112755
    Prev
    Next
    INDEX
    Explanations

    email addresses

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

    the '@' symbol in email addresses.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     "'
    -2.17
     "
    -2.11
     combinar
    -1.99
    ăzi
    -1.89
     '
    -1.89
     has
    -1.82
    ométrique
    -1.76
     
    -1.75
     queridos
    -1.74
     "[
    -1.73
    POSITIVE LOGITS
     of
    2.63
    镦
    2.23
     they
    2.06
     剧照
    1.97
    有两
    1.83
    俢
    1.78
     boya
    1.76
     dipinto
    1.74
    䊊
    1.73
    枼
    1.73
    Activations Density 0.016%

    No Known Activations