© 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. 256714
    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
     interferes
    0.54
     willfully
    0.53
     interfere
    0.52
     cerve
    0.51
     fourni
    0.50
     于
    0.49
     waardoor
    0.48
     interferon
    0.47
     us
    0.46
     amelior
    0.46
    POSITIVE LOGITS
    nip
    0.50
    eip
    0.47
    ение
    0.44
    Weekend
    0.44
    mmas
    0.44
    undan
    0.44
    👭
    0.44
    คอน
    0.43
    SetName
    0.43
    ERN
    0.43
    Activations Density 0.001%

    No Known Activations