© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38055
    Prev
    Next
    INDEX
    Explanations

    asking for prayers or supplication

    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
     gespannt
    -0.72
     inertial
    -0.71
     harmonics
    -0.68
    исленность
    -0.68
     Mendelssohn
    -0.67
    chauung
    -0.66
     śred
    -0.66
    ActionResult
    -0.65
    maty
    -0.65
    PROD
    -0.65
    POSITIVE LOGITS
     supp
    2.23
     dua
    1.92
     prayer
    1.88
     prayers
    1.84
     Dua
    1.72
     praying
    1.49
     invoking
    1.49
     asking
    1.49
     petition
    1.48
     invocation
    1.47
    Activations Density 0.026%

    No Known Activations