© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7997
    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
    zték
    0.57
    ză
    0.55
    峼
    0.51
    谀
    0.48
    י
    0.48
    ઝ
    0.48
    燡
    0.47
     nieces
    0.47
     Missouri
    0.46
    ৃক
    0.46
    POSITIVE LOGITS
    (
    0.54
    0.50
    :
    0.49
    Ed
    0.47
    Galer
    0.46
    Finland
    0.46
    Lionel
    0.45
    Rus
    0.44
    Eu
    0.43
    Cas
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.