© 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. 12535
    Prev
    Next
    INDEX
    Explanations

    scientific prefix compounds

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

    hyphenated prefixes such as "co-", "self-", "anti-", "non-", "pre-", and others that create compound terms.

    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_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
     唯美
    -1.77
     sés
    -1.69
     菇
    -1.65
     実例
    -1.64
     demokra
    -1.63
     Eſ
    -1.61
     复古
    -1.60
     水墨
    -1.60
     夜景
    -1.60
     花纹
    -1.60
    POSITIVE LOGITS
    C
    2.03
    T
    1.98
     what
    1.98
    N
    1.97
    F
    1.95
    O
    1.91
    P
    1.88
    V
    1.88
    L
    1.88
    S
    1.87
    Activations Density 0.062%

    No Known Activations