© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 54008
    Prev
    Next
    INDEX
    Explanations

    repentance, apologize, penance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    وشی
    -0.86
    ova
    -0.76
    eris
    -0.76
    ลม
    -0.75
    faden
    -0.72
    лива
    -0.72
    amili
    -0.72
    roma
    -0.71
     resurrected
    -0.71
     tapioca
    -0.70
    POSITIVE LOGITS
     repentance
    2.75
     repent
    2.69
     remorse
    2.11
     arrep
    2.05
    悔
    1.71
     penit
    1.61
     regret
    1.58
     rep
    1.48
     conversion
    1.40
     Rep
    1.33
    Activations Density 0.008%

    No Known Activations