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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 4058
    Prev
    Next
    INDEX
    Explanations

    religious scriptural terms

    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
    িনবার্গ
    0.81
    ቪ
    0.77
    ட்டைகோ
    0.75
    ولندا
    0.71
    ቬ
    0.70
    র্জাতিক
    0.70
    ufthansa
    0.69
     rollerskates
    0.69
     fournisseurs
    0.69
    ুইস
    0.69
    POSITIVE LOGITS
     Allah
    0.84
     Quran
    0.70
     م
    0.69
     ب
    0.67
     Imam
    0.66
     Ibn
    0.66
    0.65
     D
    0.63
     Ayat
    0.63
     ح
    0.61
    Activations Density 0.020%

    No Known Activations