© 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-65K
    7. 27096
    Prev
    Next
    INDEX
    Explanations

    user interaction guides

    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_65k_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
    ים
    0.58
    бле
    0.46
    ных
    0.45
    ocrats
    0.44
    м
    0.44
    ங்களின்
    0.44
    ö
    0.44
    ᆹ
    0.44
    wie
    0.43
    bedded
    0.43
    POSITIVE LOGITS
    i
    0.63
     Human
    0.54
     Guest
    0.51
    u
    0.50
    o
    0.49
     Rory
    0.49
     UserModel
    0.48
     User
    0.47
     Employee
    0.47
    a
    0.47
    Activations Density 0.004%

    No Known Activations