© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2736
    Prev
    Next
    INDEX
    Explanations

    email and communication

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

    responding and asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     fetching
    0.24
     willst
    0.23
     kanker
    0.23
    牞
    0.23
     தா
    0.22
     appealed
    0.22
    뷔
    0.22
     CDKN
    0.22
     为
    0.22
     Caucasus
    0.22
    POSITIVE LOGITS
    Email
    0.35
     email
    0.35
    メール
    0.34
     emails
    0.33
    电话
    0.33
    电子邮件
    0.33
     ईमेल
    0.32
    短信
    0.32
    email
    0.32
     Emails
    0.31
    Activations Density 0.300%

    No Known Activations