© 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. 169140
    Prev
    Next
    INDEX
    Explanations

    darkening, vertically, legs, zone behind

    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
    ại
    0.42
    ༢
    0.41
    GAD
    0.39
    ্যাটে
    0.39
     이슈
    0.39
    नाती
    0.38
     franchisee
    0.38
    酞
    0.37
    Mismatch
    0.37
    一定要
    0.37
    POSITIVE LOGITS
     normales
    0.40
     properly
    0.39
     incurring
    0.38
     bienvenida
    0.37
     স্বাভাবিক
    0.37
     passed
    0.36
     Normal
    0.36
     pleasantly
    0.36
    zieh
    0.36
     transitioned
    0.36
    Activations Density 0.002%

    No Known Activations