© 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. 106603
    Prev
    Next
    INDEX
    Explanations

    backup power systems

    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
     \
    0.90
    p
    0.88
    お
    0.79
     I
    0.78
    もら
    0.73
     پھر
    0.73
    見える
    0.72
    П
    0.72
    見
    0.71
     in
    0.70
    POSITIVE LOGITS
    ле
    1.11
     or
    1.05
    т
    0.93
    л
    0.91
    ED
    0.85
    твы
    0.85
    ל
    0.85
     on
    0.84
    рены
    0.83
    ल
    0.82
    Activations Density 0.003%

    No Known Activations