© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 90108
    Prev
    Next
    INDEX
    Explanations

    Alice Wonderland Carroll Prince

    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
    。
    0.76
    ।
    0.71
     الملف
    0.64
    я
    0.62
    ه
    0.61
     appliance
    0.61
    氅
    0.60
     Василий
    0.59
     Seoul
    0.59
     Stockholm
    0.59
    POSITIVE LOGITS
     for
    0.62
    ig
    0.58
    ierung
    0.52
    q
    0.52
    ⅙
    0.52
    {},
    0.52
    ired
    0.51
     Challenges
    0.51
    otis
    0.51
     highlights
    0.50
    Activations Density 0.002%

    No Known Activations