© 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. 10-GEMMASCOPE-RES-131K
    4. 1243
    Prev
    Next
    INDEX
    Explanations

    specific nouns, often followed by descriptive phrases

    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_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
     to
    -2.14
    5
    -1.72
     by
    -1.52
     ibang
    -1.51
    0
    -1.41
     hâte
    -1.34
     with
    -1.34
    lerle
    -1.31
     chilen
    -1.30
    ほうがいい
    -1.27
    POSITIVE LOGITS
     ?????
    1.48
     tivi
    1.38
     ???
    1.37
    𝑸
    1.33
     ????
    1.32
     utilizando
    1.31
    ută
    1.27
     aceites
    1.27
    ximate
    1.25
    
    1.24
    Activations Density 0.160%

    No Known Activations