© 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. 35154
    Prev
    Next
    INDEX
    Explanations

    vehicle, vehicles, and vehicle-specific concepts

    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
    1.58
    to
    1.45
    u
    1.34
    ي
    1.14
    in
    1.13
    ার
    1.12
    er
    1.11
    𝗹
    1.11
    uq
    1.08
    म
    1.08
    POSITIVE LOGITS
    1
    1.11
    <0x91>
    1.04
    ية
    1.00
    2
    0.99
    ยนต์
    0.94
    ни
    0.89
    <0x93>
    0.83
    ين
    0.82
    一
    0.81
    ill
    0.80
    Activations Density 0.007%

    No Known Activations