© 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. 89825
    Prev
    Next
    INDEX
    Explanations

    related 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
     comentario
    0.46
    を開始
    0.45
    ܛ
    0.45
    这座
    0.43
    𝒜
    0.43
     salud
    0.43
     idiomas
    0.42
    ټبال
    0.42
    無法
    0.42
     observer
    0.41
    POSITIVE LOGITS
     D
    0.50
     specifically
    0.50
    ột
    0.47
     Par
    0.44
     Specifically
    0.44
    1
    0.42
     чаще
    0.42
     নিয়ে
    0.42
     সময়
    0.41
     seasons
    0.41
    Activations Density 0.016%

    No Known Activations