© 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. 21030
    Prev
    Next
    INDEX
    Explanations

    twitter threads and instagram posts

    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
    ശ
    0.46
    responseData
    0.40
    atique
    0.39
     finalement
    0.39
    னமாக
    0.39
     ultimately
    0.39
    г
    0.39
    ጪ
    0.39
     Wimbledon
    0.38
    mique
    0.38
    POSITIVE LOGITS
    ilh
    0.40
     FLAT
    0.40
    ConfigureAwait
    0.40
    Bin
    0.39
    ILLE
    0.39
     pulang
    0.39
     "\\
    0.38
     flat
    0.38
     BIN
    0.38
    Flat
    0.37
    Activations Density 0.006%

    No Known Activations