© 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. 27460
    Prev
    Next
    INDEX
    Explanations

    * ** **

    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
    ستين
    0.47
    𝙩
    0.46
    ۳
    0.45
    ков
    0.44
    മ്പ്
    0.44
     conclusively
    0.44
    петров
    0.44
    ሦ
    0.44
    स्ट
    0.43
    鳕
    0.43
    POSITIVE LOGITS
     bureaucracy
    0.45
     immune
    0.44
     Q
    0.43
    Ւ
    0.43
    /
    0.43
     u
    0.42
     or
    0.42
    免疫
    0.41
     software
    0.40
     Qi
    0.40
    Activations Density 0.024%

    No Known Activations