© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 32857
    Prev
    Next
    INDEX
    Explanations

    ammunition

    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
     I
    0.91
     A
    0.73
     D
    0.71
    protein
    0.70
     a
    0.67
    cyt
    0.66
     M
    0.64
     G
    0.64
    .
    0.62
     B
    0.61
    POSITIVE LOGITS
    т
    1.05
    ри
    1.04
    ة
    0.94
    는
    0.88
    ת
    0.83
    в
    0.83
    は
    0.82
    ి
    0.79
     Caucus
    0.78
     తన
    0.77
    Activations Density 0.001%

    No Known Activations