© 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. 1259
    Prev
    Next
    INDEX
    Explanations

    references to community information

    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
     at
    -1.67
     for
    -1.52
     if
    -1.45
     with
    -1.44
     needed
    -1.39
     part
    -1.23
     use
    -1.20
     example
    -1.20
    ujeme
    -1.18
     Does
    -1.16
    POSITIVE LOGITS
    despite
    1.39
    ktionen
    1.30
    コロナ禍
    1.28
     tertawa
    1.28
    あなたは
    1.27
     are
    1.27
    providing
    1.26
    
    1.26
    seeing
    1.23
    彼は
    1.23
    Activations Density 0.084%

    No Known Activations