© 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. 76169
    Prev
    Next
    INDEX
    Explanations

    thank goodness god heaven

    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
     done
    -1.32
     Done
    -0.98
    Done
    -0.96
    done
    -0.85
     DONE
    -0.79
    DONE
    -0.78
    liter
    -0.76
    TÜ
    -0.74
    чери
    -0.71
     it
    -0.68
    POSITIVE LOGITS
     heaven
    4.22
     goodness
    4.03
     God
    3.75
     heavens
    3.69
     Heaven
    3.55
     god
    3.25
    Heaven
    3.22
    God
    3.16
    heaven
    3.09
     Heavens
    3.03
    Activations Density 0.032%

    No Known Activations