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

    Neuronpedia

    Jacobian LensNEW
    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. 54672
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
     concursos
    0.40
    颁
    0.38
     Ре
    0.36
    Python
    0.36
    ıldığı
    0.36
     系统
    0.35
     adunay
    0.35
     Под
    0.35
     作品
    0.35
    冑
    0.35
    POSITIVE LOGITS
    आप
    0.38
    vous
    0.36
     filler
    0.35
    ਲ
    0.35
    Bhar
    0.34
    например
    0.34
    Sé
    0.33
     तुमचा
    0.33
    лайте
    0.33
     grille
    0.33
    Activations Density 0.003%

    No Known Activations