© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1836
    Prev
    Next
    INDEX
    Explanations

    addition expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    com
    0.76
    en
    0.67
    â
    0.66
    us
    0.64
    odies
    0.64
    ical
    0.64
    ™
    0.63
    ware
    0.62
    ́
    0.62
    blocks
    0.61
    POSITIVE LOGITS
    <unused340>
    1.16
     romanzo
    1.16
    ⦕
    1.10
    ⤠
    1.07
    Quantidade
    1.04
    <unused382>
    1.04
    ᗜ
    1.04
     ventajas
    1.03
    <unused1094>
    1.03
    <unused416>
    1.03
    Activations Density 1.219%

    No Known Activations