© 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. 12242
    Prev
    Next
    INDEX
    Explanations

    defining or describing actions

    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
    咂
    0.38
    ब्दिक
    0.37
    ♀
    0.37
     cenderung
    0.36
    是一些
    0.36
    ToolStrip
    0.36
    経過
    0.34
    odoxy
    0.34
     contamos
    0.33
    >',
    0.33
    POSITIVE LOGITS
     ressemble
    0.47
    itates
    0.41
     both
    0.40
     abbia
    0.40
     Dieses
    0.39
    кает
    0.39
    kommt
    0.39
     governs
    0.39
    водит
    0.39
     characterizes
    0.38
    Activations Density 0.007%

    No Known Activations