© 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. 22-GEMMASCOPE-RES-131K
    7. 68294
    Prev
    Next
    INDEX
    Explanations

    religious and cosmic concepts

    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_22/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
    部分が
    -1.41
     .........
    -1.34
     colossal
    -1.32
     .......
    -1.30
     superb
    -1.29
     gigantic
    -1.27
     hugely
    -1.25
     overly
    -1.24
     insanely
    -1.24
     dando
    -1.23
    POSITIVE LOGITS
     Essentially
    1.47
     There
    1.43
     Taking
    1.39
     Getting
    1.34
     Combining
    1.32
     Generally
    1.31
     Putting
    1.29
     Using
    1.28
     Going
    1.27
     Since
    1.27
    Activations Density 0.125%

    No Known Activations