© 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. 16751
    Prev
    Next
    INDEX
    Explanations

    mathematical results and equations

    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
    、
    0.48
     Бо
    0.47
    2
    0.44
    oh
    0.41
    ק
    0.41
    ער
    0.41
     F
    0.40
    1
    0.40
    igt
    0.39
    वा
    0.39
    POSITIVE LOGITS
     👇
    0.45
     
    0.43
     ».
    0.40
    .—
    0.40
     ഓരോ
    0.39
     gồm
    0.39
     coales
    0.38
    multiSelectList
    0.38
    HLIGHT
    0.38
    ۔۔
    0.38
    Activations Density 0.030%

    No Known Activations