© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 29090
    Prev
    Next
    INDEX
    Explanations

    medical conditions, countries, disturbances

    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
    状況
    0.45
    蜇
    0.45
    㹮
    0.44
    装饰
    0.44
    園
    0.44
    지는
    0.43
    PagerAdapter
    0.43
    땄
    0.43
    漫画
    0.42
    遭遇
    0.41
    POSITIVE LOGITS
    ı
    0.61
    ll
    0.58
    ym
    0.57
    ust
    0.55
    ü
    0.55
    я
    0.52
    í
    0.52
    an
    0.52
     end
    0.52
    uh
    0.52
    Activations Density 0.005%

    No Known Activations