© 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. 78733
    Prev
    Next
    INDEX
    Explanations

    games, self defense, specific programming terms

    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
     exciting
    0.48
     spann
    0.48
     quantization
    0.41
     pois
    0.40
    miktar
    0.40
     関
    0.39
     planification
    0.39
     機
    0.39
     mk
    0.38
     informatics
    0.38
    POSITIVE LOGITS
     Sì
    0.40
    imai
    0.40
    wijl
    0.38
    Cond
    0.38
    ARAJYA
    0.38
    Lemon
    0.37
    Philos
    0.37
    Condition
    0.37
    Bulletin
    0.37
    Shared
    0.36
    Activations Density 0.005%

    No Known Activations