© 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. 130229
    Prev
    Next
    INDEX
    Explanations

    carrying back losses

    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
    새
    0.41
    PLING
    0.41
    Desktop
    0.40
    últ
    0.40
     세계
    0.40
    NEW
    0.39
     KEN
    0.38
    foto
    0.37
    ਡ
    0.37
    winkel
    0.37
    POSITIVE LOGITS
     Bisby
    0.59
     MgII
    0.41
     retain
    0.41
     retained
    0.41
     Precambrian
    0.40
     चुकी
    0.40
     فرو
    0.40
     Differ
    0.40
     GameObject
    0.40
     Roskov
    0.40
    Activations Density 0.000%

    No Known Activations