© 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. 258623
    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
     automóvil
    0.47
     connector
    0.45
    SampleSize
    0.43
     {}>,
    0.43
     自分
    0.43
     ప్రజా
    0.42
     immunological
    0.42
     Wörter
    0.41
     érz
    0.41
     จริง
    0.40
    POSITIVE LOGITS
    ،
    0.55
    第五
    0.52
    ut
    0.52
    9
    0.52
    ۹
    0.51
    H
    0.50
    BX
    0.50
    ای
    0.49
    by
    0.49
    8
    0.49
    Activations Density 0.000%

    No Known Activations