© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9355
    Prev
    Next
    INDEX
    Explanations

    private information, communications, or spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    0.65
    时
    0.47
     Specified
    0.46
     অব
    0.45
     Συν
    0.45
     Efter
    0.45
    '।
    0.43
     nél
    0.43
    วรร
    0.43
    ط
    0.43
    POSITIVE LOGITS
     private
    1.47
    private
    1.41
    Private
    1.38
    PRIVATE
    1.33
     Private
    1.31
     PRIVATE
    1.29
     privada
    1.27
     प्राइवेट
    1.27
     privato
    1.25
     निजी
    1.21
    Activations Density 0.064%

    No Known Activations