© 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. 131540
    Prev
    Next
    INDEX
    Explanations

    mathcal, Hamiltonian, physical time

    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
     ink
    0.39
     innym
    0.38
     ந
    0.37
     dangerously
    0.37
     point
    0.36
     uneasy
    0.36
    を用いる
    0.36
    講
    0.36
     u
    0.36
     dangerous
    0.35
    POSITIVE LOGITS
    ₁)
    0.46
    islava
    0.45
    rustic
    0.45
    庙
    0.41
    ﮄ
    0.41
    tailed
    0.39
    ˹
    0.39
    শিয়া
    0.38
    नॉ
    0.38
    শিয়া
    0.38
    Activations Density 0.002%

    No Known Activations