© 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. 33420
    Prev
    Next
    INDEX
    Explanations

    superstition and beliefs

    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
     pornography
    -0.93
     styrene
    -0.90
     OSError
    -0.82
     venter
    -0.80
    ình
    -0.80
     GOODS
    -0.79
     adjectives
    -0.79
    товано
    -0.79
     мя
    -0.77
    itzer
    -0.77
    POSITIVE LOGITS
     superstitious
    3.78
     superstition
    3.64
    supers
    3.42
     superstitions
    3.34
     Supers
    3.28
    Supers
    3.20
     supers
    2.83
     beliefs
    2.44
     belief
    2.44
    belief
    2.20
    Activations Density 0.024%

    No Known Activations