© 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. 40-GEMMASCOPE-2-RES-262K
    7. 137786
    Prev
    Next
    INDEX
    Explanations

    image stabilization

    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
    Negative Logits
    螨
    0.45
     kính
    0.43
    堊
    0.43
    adapted
    0.41
    ituary
    0.41
    解釋
    0.41
    缫
    0.40
     специфи
    0.39
    魃
    0.39
    targetReference
    0.39
    POSITIVE LOGITS
     stabilization
    0.56
     Stabilization
    0.54
     stabilize
    0.50
     stabilizing
    0.49
     Stabil
    0.48
     stabilizer
    0.47
     Verd
    0.46
     stabilise
    0.45
     IS
    0.45
    Stabil
    0.45
    Activations Density 0.010%

    No Known Activations