© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144551
    Prev
    Next
    INDEX
    Explanations

    service company names

    np_acts-logits-general · gemini-2.5-flash-lite

    bridging gaps, blazers, layers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Finnish
    0.54
     ہی
    0.43
     میں
    0.42
     Norwegian
    0.41
     |
    0.40
     bakery
    0.40
     는
    0.40
     کے
    0.39
     Finland
    0.39
     Turkish
    0.39
    POSITIVE LOGITS
    尊重
    0.48
    岩
    0.47
     acknowledging
    0.45
     priorité
    0.44
    当量
    0.43
    役割
    0.43
     epigen
    0.42
    增长
    0.42
     interdiscipl
    0.41
    眼神
    0.41
    Activations Density 0.000%

    No Known Activations