© 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. 257391
    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
     విధాన
    0.43
    परीक्षा
    0.42
    आव
    0.42
    mated
    0.41
     сосе
    0.39
    wizard
    0.39
    )–
    0.38
    𝚊
    0.38
    words
    0.38
     была
    0.38
    POSITIVE LOGITS
     Zd
    0.51
    ad
    0.49
     KQkq
    0.49
    ียว
    0.48
     odnosno
    0.47
    ಾನೆ
    0.46
     bitte
    0.45
     Korn
    0.45
     kojem
    0.45
    急速
    0.44
    Activations Density 0.000%

    No Known Activations