© 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. 258651
    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
     Tumblr
    0.53
    चुरी
    0.51
    䨘
    0.49
    ⠑
    0.48
     laquelle
    0.48
     która
    0.48
     Bryn
    0.45
     dobry
    0.44
    ្នាំ
    0.43
     Capitalism
    0.43
    POSITIVE LOGITS
    cmd
    0.45
    ci
    0.43
    ↵
    0.43
     оказа
    0.40
     flavors
    0.40
     Schloss
    0.40
     Продол
    0.40
    cs
    0.39
     сре
    0.38
     fehl
    0.38
    Activations Density 0.001%

    No Known Activations