© 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. 16811
    Prev
    Next
    INDEX
    Explanations

    variable or code structure declaration

    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
    -
    0.46
     quiver
    0.43
    нь
    0.40
    સ
    0.40
    ية
    0.39
    تك
    0.39
    çant
    0.39
    ൻ
    0.39
    嵬
    0.38
    ه
    0.38
    POSITIVE LOGITS
    IDS
    0.48
    nThe
    0.48
    ı
    0.47
    啍
    0.46
     kodu
    0.45
    lja
    0.43
     aturan
    0.43
    .`
    0.42
     It
    0.42
    @@]
    0.41
    Activations Density 0.173%

    No Known Activations