© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2482
    Prev
    Next
    INDEX
    Explanations

    sending or spreading messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zymy
    1.59
    wości
    1.53
     społec
    1.50
     sifat
    1.43
    ’).
    1.37
    ’),
    1.35
    atsby
    1.34
    루
    1.31
     keber
    1.31
     wajah
    1.27
    POSITIVE LOGITS
     mails
    1.91
     Sending
    1.60
    Sending
    1.59
     sending
    1.58
    ivative
    1.57
     sends
    1.57
    ToServer
    1.57
     emails
    1.55
    bote
    1.55
    క్కి
    1.54
    Activations Density 0.513%

    No Known Activations