© 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. 193695
    Prev
    Next
    INDEX
    Explanations

    partial pressures

    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
    二
    0.43
    ன்ற
    0.40
     సి
    0.40
     Earl
    0.39
    ┻
    0.38
    ourg
    0.38
     earl
    0.38
     debating
    0.38
     две
    0.37
    엄
    0.37
    POSITIVE LOGITS
    axel
    0.42
     sider
    0.40
     sandbox
    0.38
    ursal
    0.38
    alis
    0.38
    izaje
    0.38
    Isa
    0.38
    named
    0.37
     raus
    0.37
    λαν
    0.37
    Activations Density 0.002%

    No Known Activations