© 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. 258867
    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
    häuse
    0.51
    bug
    0.50
     fud
    0.47
     schn
    0.46
    ':'
    0.45
    et
    0.45
    bach
    0.44
    ley
    0.44
    kannt
    0.44
     pote
    0.44
    POSITIVE LOGITS
    antoor
    0.52
    ências
    0.50
    𝗶
    0.46
    曛
    0.45
     것에
    0.45
     রাজধান
    0.44
    ньому
    0.43
    িসের
    0.42
     mirroring
    0.42
     করছে
    0.42
    Activations Density 0.001%

    No Known Activations