© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15059
    Prev
    Next
    INDEX
    Explanations

    email us

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

    email

    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_16k_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
    '
    0.58
     समा
    0.50
     Уже
    0.47
     irresist
    0.46
     Телефон
    0.46
     Букови
    0.45
    тный
    0.44
     пяти
    0.44
     сопротив
    0.44
     チ
    0.44
    POSITIVE LOGITS
     email
    1.05
     emails
    1.02
     Email
    1.00
    Email
    0.99
    EMAIL
    0.96
     emailing
    0.92
    Emails
    0.91
    电子邮件
    0.91
    email
    0.90
     Emails
    0.90
    Activations Density 0.157%

    No Known Activations