© 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. 256870
    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
    IG
    0.46
    }^{-\
    0.43
     د
    0.43
    اً
    0.43
    غ
    0.42
    لي
    0.42
    لم
    0.41
    Disclosure
    0.41
    請
    0.41
     emissions
    0.41
    POSITIVE LOGITS
    atud
    0.53
     oggetti
    0.52
     ancienne
    0.52
     Spannung
    0.52
     ಹಿಂದೆ
    0.51
     differ
    0.50
     sieci
    0.49
    ęcz
    0.48
     முன்பு
    0.48
     ग्रंथों
    0.48
    Activations Density 0.000%

    No Known Activations