© 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. 31-GEMMASCOPE-2-RES-262K
    7. 257620
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    阴
    0.50
    s
    0.48
    дку
    0.43
    中共
    0.42
    越来越多的
    0.42
    软
    0.41
     convenc
    0.41
    द्ध
    0.41
    轿
    0.41
    screw
    0.40
    POSITIVE LOGITS
     считают
    0.51
    ”…
    0.48
    Afrique
    0.48
     dianggap
    0.46
     Lata
    0.45
     Хоро
    0.45
    iscus
    0.44
     वेर
    0.44
     Xcode
    0.44
     ediciones
    0.43
    Activations Density 0.000%

    No Known Activations