© 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. 16-GEMMASCOPE-2-RES-262K
    7. 118584
    Prev
    Next
    INDEX
    Explanations

    under-eye circles and puffiness

    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_16_width_262k_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
     हुने
    0.54
     „
    0.52
    Ә
    0.51
    Bitte
    0.48
     des
    0.48
     clothes
    0.48
     parro
    0.47
    しの
    0.46
    ढी
    0.46
    Ổ
    0.46
    POSITIVE LOGITS
    ার্স
    0.59
    enb
    0.58
     tincture
    0.55
    in
    0.55
    enin
    0.54
    olos
    0.52
     poniendo
    0.52
    만큼
    0.52
     utilisons
    0.51
     χρήση
    0.51
    Activations Density 0.005%

    No Known Activations