© 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. 26555
    Prev
    Next
    INDEX
    Explanations

    glimpse behind or into

    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
    愊
    0.39
     victim
    0.38
    स्पिटल
    0.37
     déterminé
    0.37
    दिग्ध
    0.37
    स्तेमाल
    0.36
    alus
    0.36
    alade
    0.36
     vítima
    0.36
    ڈیو
    0.35
    POSITIVE LOGITS
     glimpse
    1.46
     peek
    1.46
     glimpses
    1.38
    peek
    1.24
    覗
    1.22
     Peek
    1.16
     peered
    1.16
     peering
    1.15
     glimps
    1.10
     peep
    1.09
    Activations Density 0.010%

    No Known Activations