© 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. 57133
    Prev
    Next
    INDEX
    Explanations

    enclosed spherical globes

    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
    У
    0.46
    tt
    0.43
    全世界
    0.40
    line
    0.39
    stderr
    0.39
    В
    0.39
     Worldwide
    0.38
    unct
    0.38
    까지
    0.38
     ஐ
    0.38
    POSITIVE LOGITS
     dallo
    0.46
     refrigeration
    0.44
     semelh
    0.42
    صیٰ
    0.42
     radiology
    0.42
     tradicion
    0.41
     sprang
    0.40
     mindless
    0.40
    ब्दिक
    0.40
     traditionnel
    0.40
    Activations Density 0.004%

    No Known Activations