© 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. 206470
    Prev
    Next
    INDEX
    Explanations

    medical compartment mainly

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

    writing prompts and examples

    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
    ᱜ
    0.53
    pandemic
    0.52
    ڦ
    0.52
    騫
    0.48
    ቴክ
    0.48
    ᱯ
    0.46
    nj
    0.46
    Pharm
    0.46
    ઐ
    0.46
    ﺤ
    0.45
    POSITIVE LOGITS
     úrov
    0.54
    褛
    0.51
     자주
    0.47
     squats
    0.46
     条
    0.46
     afterthought
    0.46
     Underwood
    0.46
     häufig
    0.45
     accomplishment
    0.44
     Tó
    0.44
    Activations Density 0.000%

    No Known Activations