© 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. 10-GEMMASCOPE-RES-131K
    7. 75387
    Prev
    Next
    INDEX
    Explanations

    alchemy and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    words related to alchemy and mystical/occult concepts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     anc
    -2.36
    蕷
    -2.08
    á
    -2.05
     are
    -2.03
    ra
    -2.03
    ati
    -2.02
    et
    -2.00
     что
    -1.98
    in
    -1.96
    ⽌
    -1.93
    POSITIVE LOGITS
    atação
    2.48
     There
    2.28
    there
    2.16
     Umständen
    2.09
     PUSTAKA
    2.03
    entukan
    2.03
    ют
    1.98
    hige
    1.97
    外国
    1.97
     люди
    1.97
    Activations Density 0.003%

    No Known Activations