© 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. 53866
    Prev
    Next
    INDEX
    Explanations

    medical findings description

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

    describing findings

    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
     rightfully
    0.39
    discuss
    0.38
    搔
    0.38
    狨
    0.38
    ันทร์
    0.38
     phoned
    0.37
    鲛
    0.37
     reincarn
    0.36
    ција
    0.36
    桨
    0.36
    POSITIVE LOGITS
    consistent
    0.51
     strongly
    0.48
    を中心に
    0.48
     Strongly
    0.48
     consistent
    0.46
    bool
    0.45
     salient
    0.45
    明顯
    0.44
     credible
    0.43
     Bayesian
    0.42
    Activations Density 0.015%

    No Known Activations