© 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. 212704
    Prev
    Next
    INDEX
    Explanations

    clinical practice

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

    explaining how to combine or outline something

    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
     painless
    0.52
     vitre
    0.52
     meticulous
    0.49
     etter
    0.48
     pedicure
    0.48
     preferential
    0.48
    <unused60>
    0.47
     photosphere
    0.47
     heterozygous
    0.47
     controversial
    0.47
    POSITIVE LOGITS
    人格
    0.53
    ума
    0.49
    ('['
    0.48
    日常
    0.46
    ವಾಗಿ
    0.46
    出
    0.46
    侮
    0.45
    cInfo
    0.45
    說
    0.45
    র্থ
    0.44
    Activations Density 0.000%

    No Known Activations