© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8652
    Prev
    Next
    INDEX
    Explanations

    pronoun them that

    np_acts-logits-general · gemini-2.5-flash-lite

    relative clause connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    一来
    0.44
    에게
    0.41
    Bra
    0.41
    谁
    0.38
     Anc
    0.37
    한테
    0.36
     aquellos
    0.36
     누구
    0.36
    </div>
    0.35
     reside
    0.35
    POSITIVE LOGITS
     которая
    1.11
     which
    1.01
     которое
    1.00
     whereby
    0.96
     które
    0.93
     والتي
    0.91
     that
    0.88
     která
    0.88
     مبنی
    0.88
     waarmee
    0.87
    Activations Density 0.560%

    No Known Activations