© 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. 22068
    Prev
    Next
    INDEX
    Explanations

    observing ego without judgment

    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
    unlock
    0.42
     സൗ
    0.39
     bont
    0.39
     renfer
    0.38
    لاك
    0.38
     निक
    0.38
     opiek
    0.38
    舝
    0.38
     jednoduch
    0.38
    insk
    0.37
    POSITIVE LOGITS
     Ego
    0.82
     ego
    0.80
     egos
    0.64
    ego
    0.56
     distractions
    0.54
     egot
    0.54
     illusions
    0.53
     illusory
    0.52
     अहंकार
    0.52
     dramas
    0.50
    Activations Density 0.024%

    No Known Activations