© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 54040
    Prev
    Next
    INDEX
    Explanations

    recent belonging

    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_40_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
     ديك
    0.46
    Comparing
    0.42
    omorf
    0.41
     Ар
    0.40
     meaningless
    0.39
     rhetorical
    0.39
    写作
    0.39
     袋
    0.39
    пени
    0.39
    culus
    0.39
    POSITIVE LOGITS
     recent
    0.56
     belongs
    0.56
     belong
    0.55
     recently
    0.54
     belonging
    0.54
     Recently
    0.54
     belonged
    0.54
     Recent
    0.49
     Belong
    0.49
     perten
    0.48
    Activations Density 0.087%

    No Known Activations