© 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. 55902
    Prev
    Next
    INDEX
    Explanations

    bible verses and book names

    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
     ιστο
    -0.77
     VPN
    -0.76
    项目的
    -0.72
    ślę
    -0.71
     Lind
    -0.71
    Affili
    -0.70
     県
    -0.70
    AppRoutingModule
    -0.70
     Ventura
    -0.69
    Retrouvez
    -0.69
    POSITIVE LOGITS
     Acts
    2.20
     John
    2.02
    Acts
    1.98
     Matthew
    1.81
    John
    1.77
     Luke
    1.70
     Genesis
    1.63
    Matthew
    1.59
    Genesis
    1.45
    Luke
    1.42
    Activations Density 0.062%

    No Known Activations