© 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. 87265
    Prev
    Next
    INDEX
    Explanations

    Long Short-Term Memory

    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
     fragile
    0.40
    ικής
    0.40
    ၞ
    0.37
    Ric
    0.36
    Vals
    0.35
    ٫
    0.34
     Ric
    0.34
     počet
    0.33
    <0x89>
    0.33
    から
    0.33
    POSITIVE LOGITS
    Long
    0.44
     ロング
    0.43
     Long
    0.42
     اعتق
    0.41
     LONG
    0.40
    ുകൾ
    0.40
     BEEN
    0.39
    際は
    0.38
     LON
    0.38
     লং
    0.38
    Activations Density 0.012%

    No Known Activations