© 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. 40-GEMMASCOPE-2-RES-262K
    7. 137279
    Prev
    Next
    INDEX
    Explanations

    past tense verbs with agency

    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_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
    াবের
    0.37
    ệp
    0.36
    ㄈ
    0.36
     '~
    0.35
    occa
    0.35
    渑
    0.35
     "~
    0.35
     basilaires
    0.35
    tabPage
    0.34
     ใ
    0.34
    POSITIVE LOGITS
     oleh
    0.90
     by
    0.88
     توسط
    0.88
     بواسطة
    0.76
     tomonidan
    0.69
    由
    0.65
    による
    0.61
     bởi
    0.60
     의해
    0.56
    為
    0.55
    Activations Density 0.022%

    No Known Activations