© 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. 61825
    Prev
    Next
    INDEX
    Explanations

    words starting with j

    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
     textAppearance
    0.41
    ங்கு
    0.41
     customary
    0.38
    ຫານ
    0.38
    Buscar
    0.37
    
    0.37
     convey
    0.36
    textAppearance
    0.36
    ጺ
    0.35
     పెద్ద
    0.35
    POSITIVE LOGITS
     J
    0.68
    J
    0.55
     JM
    0.54
     JH
    0.52
    cJ
    0.52
     JSP
    0.52
     JC
    0.51
     Ј
    0.51
     JJ
    0.50
     Jost
    0.50
    Activations Density 0.134%

    No Known Activations