© 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. 60820
    Prev
    Next
    INDEX
    Explanations

    Biblical interpretation

    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
    InBytes
    -0.91
    vyš
    -0.89
     clone
    -0.84
    ksessa
    -0.84
     penyakit
    -0.83
    descri
    -0.82
     oraciones
    -0.81
    ternut
    -0.81
    risten
    -0.80
     enum
    -0.79
    POSITIVE LOGITS
     interpretive
    1.44
     interpretation
    1.34
     interpreta
    1.28
     interpretación
    1.21
     interpreting
    1.18
     interpreters
    1.17
     exe
    1.15
     Interpretation
    1.15
     interpret
    1.13
     Interpre
    1.12
    Activations Density 0.018%

    No Known Activations