© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2644
    Prev
    Next
    INDEX
    Explanations

    class definitions and public access

    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_40_width_262k_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
    私
    0.66
    Private
    0.65
     Private
    0.64
    PRIVATE
    0.55
     PRIVATE
    0.55
     प्राइवेट
    0.52
    私が
    0.50
     privés
    0.49
     私
    0.48
     privato
    0.47
    POSITIVE LOGITS
    public
    1.05
     public
    0.99
    class
    0.92
     class
    0.87
    sealed
    0.74
     सार्वजनिक
    0.73
     sealed
    0.71
     публи
    0.69
     pública
    0.66
    internal
    0.65
    Activations Density 0.006%

    No Known Activations