© 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. 117089
    Prev
    Next
    INDEX
    Explanations

    celery stalks or sticks

    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
    ن
    0.85
    ان
    0.80
    리
    0.71
    لي
    0.70
    است
    0.66
    т
    0.66
    н
    0.64
    an
    0.64
     an
    0.64
    الس
    0.64
    POSITIVE LOGITS
     catalyzed
    0.65
     sported
    0.65
     viewership
    0.64
     financed
    0.63
     modeled
    0.63
     tracked
    0.61
     পেয়েছে
    0.61
     segment
    0.60
     voiced
    0.60
    馮
    0.60
    Activations Density 0.001%

    No Known Activations