© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 64395
    Prev
    Next
    INDEX
    Explanations

    medical injury and therapy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dn
    0.46
     semicircle
    0.45
    k
    0.44
    with
    0.44
    鎂
    0.43
    s
    0.43
     背景
    0.42
    當時
    0.42
    隻
    0.42
    f
    0.41
    POSITIVE LOGITS
    受伤
    0.55
     koje
    0.51
    ښت
    0.47
     ayudará
    0.47
     необходимые
    0.45
     dotyczące
    0.44
    othérapie
    0.43
     injury
    0.43
    髂
    0.42
    多久
    0.42
    Activations Density 0.014%

    No Known Activations