© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1999
    Prev
    Next
    INDEX
    Explanations

    biblical conjunctions and phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    contend for the faith

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maatau
    0.58
    ቪ
    0.51
     powerplant
    0.49
     transcoding
    0.49
    কোনও
    0.48
    ሷ
    0.48
     upgrad
    0.47
    اونلو
    0.47
     جیت
    0.46
     നിന്നും
    0.46
    POSITIVE LOGITS
     Pharisees
    0.66
    ⌊
    0.62
     unto
    0.62
     Gentiles
    0.61
     ἐν
    0.59
     [
    0.57
     Eph
    0.56
     Herod
    0.56
     말미암아
    0.56
     Scripture
    0.55
    Activations Density 0.204%

    No Known Activations