© 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-262K
    7. 221815
    Prev
    Next
    INDEX
    Explanations

    physical sensation, debate, financial contraction, mobilization

    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
     taw
    0.39
     stares
    0.37
     considerable
    0.37
    にとって
    0.36
    㕝
    0.36
    調查
    0.35
    商人
    0.35
    ştur
    0.35
    oldo
    0.35
     sweeps
    0.35
    POSITIVE LOGITS
    爱的
    0.43
     👋
    0.40
    焕
    0.38
    Careers
    0.38
    جمة
    0.38
    pineapple
    0.38
     Fock
    0.38
    ूपी
    0.37
     Gerade
    0.37
    吧
    0.37
    Activations Density 0.000%

    No Known Activations