© 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. 6474
    Prev
    Next
    INDEX
    Explanations

    internet email addresses

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

    domain names with .gov, .co, .go, .nic

    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
    _
    0.39
    IMM
    0.35
    的方式
    0.33
    𝗗
    0.32
    𝗙
    0.32
    𝗪
    0.31
    လိုအပ်
    0.31
     तरीका
    0.31
     Änderungen
    0.30
     tradeoffs
    0.30
    POSITIVE LOGITS
    gmail
    0.35
    hotmail
    0.34
     林
    0.32
     graduating
    0.31
     gmail
    0.31
     (\"
    0.30
     nacido
    0.30
     hjem
    0.30
     postgraduate
    0.30
     telefonu
    0.30
    Activations Density 0.024%

    No Known Activations