© 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. 53-GEMMASCOPE-2-RES-262K
    7. 40748
    Prev
    Next
    INDEX
    Explanations

    stretching, expanding, distortion

    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_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     peaks
    0.41
    peaks
    0.40
     Объ
    0.39
    𝙾
    0.38
    epar
    0.37
     среде
    0.37
    fZ
    0.37
    Spectrum
    0.36
    ônica
    0.36
    óc
    0.35
    POSITIVE LOGITS
    헹
    0.41
    writerow
    0.40
     departure
    0.37
    Truman
    0.37
     ٻ
    0.36
    Injury
    0.36
     Market
    0.35
     versiones
    0.35
    ೃಹ
    0.35
    ющейся
    0.35
    Activations Density 0.001%

    No Known Activations