© 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. 256060
    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
    ي
    0.52
    आधी
    0.50
    مم
    0.48
    م
    0.48
    υπ
    0.47
    ع
    0.47
    FIX
    0.46
    برا
    0.46
    ката
    0.46
    แก้ไข
    0.46
    POSITIVE LOGITS
     benutzt
    0.47
    uluk
    0.47
    ("")]
    0.46
     deserted
    0.43
    irani
    0.43
    ile
    0.42
     abandoned
    0.41
    galkan
    0.41
    linen
    0.41
     সাহায্যের
    0.41
    Activations Density 0.000%

    No Known Activations