© 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. 120652
    Prev
    Next
    INDEX
    Explanations

    medical or scientific context

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

    often followed by meaning

    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
    irá
    0.49
    增加
    0.45
    ="+
    0.43
    避免
    0.43
     длину
    0.42
    uj
    0.41
     名称
    0.41
    ótica
    0.41
    isTrack
    0.41
    增
    0.41
    POSITIVE LOGITS
     ventral
    0.50
    စိတ်အပိုင်း
    0.50
     anno
    0.48
     ovaries
    0.47
     arqué
    0.47
     caucasian
    0.46
     approximations
    0.46
     enthalpies
    0.46
     crops
    0.45
     thighs
    0.45
    Activations Density 0.000%

    No Known Activations