© 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. 9116
    Prev
    Next
    INDEX
    Explanations

    Assoc., acquire, worsen, perform, Willi

    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
     
    -3.59
    u
    -3.42
    at
    -3.42
    ed
    -2.91
    ing
    -2.80
    ar
    -2.69
     successes
    -2.56
    ized
    -2.56
    or
    -2.55
    る
    -2.48
    POSITIVE LOGITS
     nikah
    2.25
    änomen
    2.23
     {
    2.22
     ältere
    2.20
    ﻂ
    2.19
     segurando
    2.17
    ⚣
    2.17
    ngoing
    2.16
        
    2.14
    ugais
    2.13
    Activations Density 0.008%

    No Known Activations