© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 102958
    Prev
    Next
    INDEX
    Explanations

    medical, cooking, movie titles

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

    messy hair

    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
    Negative Logits
     Почему
    0.49
    ừ
    0.47
     යුතුය
    0.47
    𝗿
    0.47
    ຟ
    0.46
     Sports
    0.46
     Пример
    0.46
     becoming
    0.45
    ince
    0.44
     ግን
    0.44
    POSITIVE LOGITS
    非洲
    0.45
     nächsten
    0.44
    きちんと
    0.44
    hexahydro
    0.42
    初
    0.42
     interessante
    0.42
     África
    0.42
     troupe
    0.42
    皁
    0.42
    株式会社
    0.42
    Activations Density 0.001%

    No Known Activations