© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9372
    Prev
    Next
    INDEX
    Explanations

    Lord curzon, The rings of power

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     libraries
    0.30
    }$.
    0.29
     ascendent
    0.29
     assembl
    0.29
    <0x1D>
    0.29
     servicing
    0.29
     structs
    0.28
    🔄
    0.28
     bypassing
    0.28
     workstations
    0.28
    POSITIVE LOGITS
    救
    0.23
     rekao
    0.23
    Queen
    0.22
    Feng
    0.22
    万元
    0.22
    著名
    0.22
    пети
    0.22
    Queens
    0.22
    Treasurer
    0.22
     frantically
    0.21
    Activations Density 0.101%

    No Known Activations