© 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-65K
    7. 45332
    Prev
    Next
    INDEX
    Explanations

    XGBoost

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    인
    0.55
    涂
    0.51
    ing
    0.47
    in
    0.46
     Fils
    0.45
     Mors
    0.44
    بيع
    0.44
     Potatoes
    0.44
    fted
    0.43
    䒑
    0.43
    POSITIVE LOGITS
     เต็ม
    0.50
     respaldo
    0.48
     ê
    0.46
     comeback
    0.46
    ência
    0.46
     nettement
    0.45
    otiv
    0.45
     patronage
    0.44
     stakeholder
    0.44
     だけ
    0.43
    Activations Density 0.006%

    No Known Activations