© 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. 35977
    Prev
    Next
    INDEX
    Explanations

    physical and business connections

    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
     quell
    0.52
     tohoto
    0.47
     yell
    0.46
    一時
    0.43
    之
    0.43
     direc
    0.43
     நிச்சயம்
    0.42
     Viola
    0.42
     Freak
    0.41
    一定
    0.40
    POSITIVE LOGITS
    odet
    0.45
    ремя
    0.43
     sepanjang
    0.43
    əsi
    0.42
    сад
    0.41
    ::$
    0.41
     scalability
    0.41
    ര്‍ന്ന
    0.41
     বাড়িতে
    0.41
    uigen
    0.40
    Activations Density 0.025%

    No Known Activations