© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 47891
    Prev
    Next
    INDEX
    Explanations

    text following a specific token

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ভাবে
    0.54
     ಔ
    0.46
    際には
    0.46
    増
    0.44
    極
    0.44
    フォーマンス
    0.43
     प्रदर्शन
    0.42
    ļ
    0.42
     Гуляць
    0.42
     unthinkable
    0.42
    POSITIVE LOGITS
     enzimas
    0.52
     sociable
    0.49
     espèce
    0.48
     actresses
    0.48
     marino
    0.48
     nematodes
    0.47
     exfoli
    0.47
     kapt
    0.47
    uiu
    0.45
     jiv
    0.45
    Activations Density 0.005%

    No Known Activations