© 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. 70119
    Prev
    Next
    INDEX
    Explanations

    religious songs about God

    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
     ultra
    -0.86
     action
    -0.79
     Action
    -0.75
     Cold
    -0.75
     Four
    -0.75
     confirm
    -0.74
     four
    -0.72
     cold
    -0.70
     or
    -0.69
    終わった
    -0.69
    POSITIVE LOGITS
     pente
    0.93
    ävän
    0.89
     побе
    0.89
    THERE
    0.87
     Tercera
    0.87
     consenti
    0.85
     Dove
    0.85
     CCM
    0.84
     worship
    0.84
    thical
    0.84
    Activations Density 0.025%

    No Known Activations