© 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. 34446
    Prev
    Next
    INDEX
    Explanations

    tea and its vendors/locations

    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
    م
    0.96
    die
    0.94
    0
    0.94
    dies
    0.93
    los
    0.88
    den
    0.87
    da
    0.86
    dan
    0.85
    dy
    0.82
    d
    0.80
    POSITIVE LOGITS
     to
    0.96
    ă
    0.90
     și
    0.85
     nella
    0.78
    ਿਤ
    0.76
     chois
    0.75
     którego
    0.75
     fakat
    0.74
     tega
    0.74
     can
    0.73
    Activations Density 0.001%

    No Known Activations