© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68668
    Prev
    Next
    INDEX
    Explanations

    quotes and excerpts

    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
    żenie
    -1.13
     for
    -1.10
     with
    -0.95
     create
    -0.94
    Élet
    -0.93
     mengisi
    -0.91
    Enllaces
    -0.91
    短期
    -0.90
    =\
    -0.89
    清明
    -0.89
    POSITIVE LOGITS
     quoted
    1.24
     trecho
    1.18
     quotes
    1.15
     excerpts
    1.11
     bellezza
    1.09
     snippets
    1.08
     hadapan
    1.07
    quote
    1.06
     fragments
    1.05
    wonder
    1.05
    Activations Density 0.068%

    No Known Activations