© 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. 53-GEMMASCOPE-2-RES-262K
    7. 3719
    Prev
    Next
    INDEX
    Explanations

    org domain names

    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_53_width_262k_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
     varicose
    0.45
     Listo
    0.42
    酤
    0.40
    场合
    0.40
    𒊺
    0.39
    脷
    0.39
    湋
    0.39
     ຮ
    0.39
    暠
    0.39
    
    0.39
    POSITIVE LOGITS
    org
    1.16
     org
    0.97
    com
    0.86
     com
    0.82
    io
    0.76
     io
    0.68
    edu
    0.58
    net
    0.57
    Org
    0.55
    nl
    0.53
    Activations Density 0.001%

    No Known Activations