© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 3597
    Prev
    Next
    INDEX
    Explanations

    data scientist, erosion, hollow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     waiters
    1.04
    assem
    0.96
     zippered
    0.95
     resultSet
    0.92
     mummy
    0.91
    ኤ
    0.89
    ဏ်
    0.89
    <unused456>
    0.88
    rollup
    0.87
     Jezus
    0.87
    POSITIVE LOGITS
    茂
    0.86
    描き
    0.77
    意义
    0.76
    走进
    0.74
     कूद
    0.74
     sombra
    0.73
     तूफान
    0.73
    MENT
    0.71
    েশন
    0.70
     з
    0.68
    Activations Density 0.000%

    No Known Activations