© 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. 65494
    Prev
    Next
    INDEX
    Explanations

    non-English words

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

    available statistics, luxury goods, cutting board

    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
    Щ
    0.58
    타
    0.54
    Я
    0.53
    Army
    0.52
    По
    0.52
    Бе
    0.52
    <b>
    0.51
    Agent
    0.50
    Кон
    0.50
    Д
    0.50
    POSITIVE LOGITS
     mengisi
    0.51
    茆
    0.47
     একখানি
    0.47
     அரை
    0.46
     vean
    0.46
     mostrou
    0.46
     använder
    0.45
     rxjs
    0.45
     transaksi
    0.45
     haue
    0.45
    Activations Density 0.001%

    No Known Activations