© 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. 200249
    Prev
    Next
    INDEX
    Explanations

    legitim, 險, 3D, Perdix

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

    stories, trauma, fantasies, ecosystems

    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
    of
    0.58
     bakan
    0.50
    TT
    0.48
    নি
    0.45
    Kya
    0.45
    </blockquote>
    0.43
     ve
    0.43
    Image
    0.42
    ↵
    0.42
    acto
    0.41
    POSITIVE LOGITS
     legitim
    0.51
    險
    0.49
     প্রয়োজনে
    0.48
    ⵔ
    0.48
     آمریکا
    0.48
     플레이
    0.47
    𝗸
    0.47
     Амери
    0.46
     statunitense
    0.46
     프랑
    0.46
    Activations Density 0.001%

    No Known Activations