© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7531
    Prev
    Next
    INDEX
    Explanations

    salvation through Christ's blood

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

    salvation and repentance

    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_31_width_262k_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
    Мар
    0.57
    קה
    0.53
    मताओं
    0.52
     വിൽപ്പന
    0.52
    市場
    0.51
    便利
    0.51
    ק
    0.51
    ตลาด
    0.50
    ཥ
    0.50
    顴
    0.49
    POSITIVE LOGITS
     salvation
    0.81
     repent
    0.69
     repentance
    0.68
     pecados
    0.68
     forgiveness
    0.67
     sinners
    0.66
     pecado
    0.64
     sinner
    0.64
     sinful
    0.64
     sins
    0.62
    Activations Density 0.214%

    No Known Activations