© 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. 260769
    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
     ትንሽ
    0.53
     ಸೋ
    0.50
     మ‌
    0.49
     प्रस
    0.48
     ताकत
    0.48
    ాన
    0.46
     刘
    0.46
     አበባ
    0.46
     ಅಭಿಮಾನ
    0.46
     کمک
    0.46
    POSITIVE LOGITS
     Zenith
    0.47
     denominations
    0.43
     Espírito
    0.43
     Celtic
    0.42
     Olympic
    0.42
     guaranty
    0.42
    ISSN
    0.41
     absentee
    0.40
     elapse
    0.40
    Ы
    0.40
    Activations Density 0.001%

    No Known Activations