© 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. 162320
    Prev
    Next
    INDEX
    Explanations

    doctors and medical professionals

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

    Name/ followed by other text

    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
     ভাগ
    0.53
    可以说是
    0.48
    Definition
    0.47
    </h3>
    0.47
    の研究
    0.47
    Subtract
    0.46
    Marco
    0.45
    GreaterThan
    0.45
    COLOG
    0.45
    </h2>
    0.45
    POSITIVE LOGITS
     Chakra
    0.52
     Osama
    0.52
     authorizations
    0.50
     phosphorylated
    0.50
     Saddam
    0.49
     Asalamualaikum
    0.49
     dispersed
    0.48
     deuterium
    0.47
     grenades
    0.47
     Hiz
    0.47
    Activations Density 0.000%

    No Known Activations