© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2947
    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_16_width_65k_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
    u
    0.69
    In
    0.48
    </td>
    0.46
    te
    0.46
    ide
    0.46
     for
    0.45
    ist
    0.45
    uerte
    0.45
    in
    0.44
    lend
    0.44
    POSITIVE LOGITS
    귿
    0.63
     обсу
    0.57
     начале
    0.52
    夰
    0.52
     dụ
    0.52
     kutoka
    0.51
     önce
    0.50
    ポール
    0.49
     опубли
    0.48
     Афри
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.