© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 258316
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     walls
    0.51
     formerly
    0.50
     famed
    0.48
     s
    0.46
     previously
    0.46
     customizing
    0.46
     airplanes
    0.44
     large
    0.43
     frightened
    0.43
     c
    0.42
    POSITIVE LOGITS
    她们
    0.55
    engelsk
    0.49
    拉斯
    0.48
     итоге
    0.47
    rewsbury
    0.47
    jahteraan
    0.46
     условии
    0.46
    њима
    0.46
    <unused49>
    0.44
    ließlich
    0.44
    Activations Density 0.001%

    No Known Activations