© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8863
    Prev
    Next
    INDEX
    Explanations

    list formatting elements

    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
     также
    0.64
     też
    0.54
    =!
    0.54
     নিজের
    0.54
     ૩
    0.53
     deleniti
    0.53
    ｸ
    0.53
     если
    0.50
     حتی
    0.50
     exagger
    0.50
    POSITIVE LOGITS
    er
    0.55
    ة
    0.55
    us
    0.53
    ើយ
    0.52
    ،
    0.50
    árs
    0.49
    고
    0.48
    y
    0.48
    σίας
    0.48
    ar
    0.47
    Activations Density 0.141%

    No Known Activations