© 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. 31-GEMMASCOPE-2-RES-262K
    7. 56139
    Prev
    Next
    INDEX
    Explanations

    adjusted/tweaked to

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    一
    0.47
     hept
    0.46
    そして
    0.44
     mappa
    0.44
    那一
    0.43
    츰
    0.43
    五
    0.42
     частини
    0.42
    圖
    0.41
    六
    0.41
    POSITIVE LOGITS
    Pay
    0.56
     Sports
    0.55
     Offers
    0.54
     provides
    0.52
     Provides
    0.52
    Provides
    0.50
     Esports
    0.50
     Registrar
    0.49
    Potential
    0.49
     offers
    0.49
    Activations Density 0.003%

    No Known Activations