© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 141410
    Prev
    Next
    INDEX
    Explanations

    marking undisclosed injury

    np_acts-logits-general · gemini-2.5-flash-lite

    pressure, behavior, character, focus, potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ম্ত
    0.61
    ༧
    0.52
    संचार
    0.51
    waitForIdleSync
    0.50
    Jwt
    0.50
    nému
    0.50
    atmosphère
    0.50
    慘
    0.49
    Density
    0.49
    ্বল
    0.48
    POSITIVE LOGITS
     A
    0.51
     G
    0.50
     go
    0.50
     ISO
    0.50
     North
    0.50
     L
    0.48
     An
    0.47
     (
    0.47
     SOC
    0.47
     meta
    0.47
    Activations Density 0.001%

    No Known Activations