© 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. 80666
    Prev
    Next
    INDEX
    Explanations

    locations after 'in'

    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
     and
    -1.41
     beserta
    -1.30
    4
    -1.30
    <h2>
    -1.27
    <h1>
    -1.25
     числен
    -1.24
    或
    -1.23
    啭
    -1.21
    на
    -1.21
    such
    -1.19
    POSITIVE LOGITS
     líquidos
    1.82
    ৢ
    1.53
     rých
    1.52
     szybko
    1.46
     cadeira
    1.44
    
    1.44
    ėje
    1.42
     its
    1.42
    存于
    1.40
    してみると
    1.40
    Activations Density 0.077%

    No Known Activations