© 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. 8650
    Prev
    Next
    INDEX
    Explanations

    context discussion

    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
    পন্থী
    0.46
     spezielle
    0.45
    盟
    0.45
    都市
    0.44
    憤
    0.44
    সজ্জিত
    0.44
    衞
    0.44
     hjälp
    0.43
    城市
    0.42
     labelling
    0.42
    POSITIVE LOGITS
     Berber
    0.48
     الصفحه
    0.47
     algod
    0.45
     tlač
    0.44
     platform
    0.44
     overclock
    0.43
    י
    0.43
    ෙන්
    0.43
     사고
    0.43
     apesar
    0.42
    Activations Density 0.012%

    No Known Activations