© 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. 105976
    Prev
    Next
    INDEX
    Explanations

    taking a deep breath

    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
    .
    0.69
     at
    0.59
    oz
    0.57
    SO
    0.55
    鼐
    0.54
     ở
    0.53
     bài
    0.53
    .‏
    0.51
    Safe
    0.50
     į
    0.50
    POSITIVE LOGITS
    يد
    0.71
     chute
    0.62
    ي
    0.58
     empezar
    0.57
    acción
    0.57
     klaar
    0.57
    üng
    0.55
    اتھ
    0.55
    ün
    0.55
     pouring
    0.55
    Activations Density 0.002%

    No Known Activations