© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 181571
    Prev
    Next
    INDEX
    Explanations

    acute intestinal disorder

    np_acts-logits-general · gemini-2.5-flash-lite

    represents internal information state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {\$
    0.45
    куп
    0.44
    蛋白
    0.44
     extinguished
    0.43
    राधना
    0.43
    .*\
    0.43
     কিনে
    0.42
     ครอง
    0.41
    মৃত্য
    0.41
    ौड़
    0.41
    POSITIVE LOGITS
     hype
    0.46
     😎
    0.46
     ceo
    0.45
     धूप
    0.45
     potenci
    0.45
     Anakin
    0.45
     ataque
    0.44
    ikopter
    0.44
     ose
    0.43
     cyborg
    0.43
    Activations Density 0.001%

    No Known Activations