© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1614
    Prev
    Next
    INDEX
    Explanations

    blessed or blessing

    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
     roues
    -0.96
     звезды
    -0.94
    冒険
    -0.93
    across
    -0.92
     *"
    -0.90
     plastered
    -0.85
     results
    -0.85
    検
    -0.85
     puertos
    -0.84
    utilise
    -0.84
    POSITIVE LOGITS
     Bless
    1.02
    可以
    0.99
    USS
    0.96
    This
    0.93
     тонн
    0.92
    It
    0.91
     mortes
    0.90
    Are
    0.90
     abundantly
    0.90
     Aussicht
    0.88
    Activations Density 0.006%

    No Known Activations