© 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. 255251
    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
    ﺎ
    0.49
    лім
    0.47
    θή
    0.47
    <0x81>
    0.46
    暢
    0.46
    ération
    0.45
    nées
    0.45
    Фі
    0.45
    ﺪ
    0.44
    нні
    0.43
    POSITIVE LOGITS
     Ceren
    0.53
     vysok
    0.49
     crept
    0.49
     Vysok
    0.49
     tarifas
    0.49
    ']")
    0.47
     allongé
    0.45
     activid
    0.45
     vijf
    0.44
     vutt
    0.44
    Activations Density 0.001%

    No Known Activations