© 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. 93891
    Prev
    Next
    INDEX
    Explanations

    atonement, sacrifice, forgiveness

    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
    henden
    -0.98
     红
    -0.82
    ulateur
    -0.80
     ALICE
    -0.77
     surve
    -0.77
     insum
    -0.75
     池
    -0.73
     Stork
    -0.73
    olybdenum
    -0.73
    initialState
    -0.71
    POSITIVE LOGITS
     atonement
    1.89
     substitution
    1.32
     Aton
    1.27
     forgiveness
    1.11
     sacrifice
    1.04
     Yom
    1.01
     Substitution
    0.97
     vic
    0.96
     covering
    0.95
    ATON
    0.95
    Activations Density 0.014%

    No Known Activations