© 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. 41-GEMMASCOPE-2-RES-262K
    7. 30561
    Prev
    Next
    INDEX
    Explanations

    root access or configuration

    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_all/layer_41_width_262k_l0_big
    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
     racines
    0.59
     roots
    0.57
     profondes
    0.55
    rooted
    0.52
    根
    0.50
     rooted
    0.49
     Roots
    0.48
    roots
    0.48
    Roots
    0.48
     raí
    0.47
    POSITIVE LOGITS
    ጐ
    0.39
     он
    0.38
    碰到
    0.38
    contacto
    0.38
    margin
    0.37
     Circum
    0.37
    Contato
    0.36
     margine
    0.36
     wsk
    0.36
    창
    0.36
    Activations Density 0.001%

    No Known Activations