© 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. 127271
    Prev
    Next
    INDEX
    Explanations

    get or have a

    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
     of
    -1.37
    tigos
    -1.34
    чните
    -1.27
     ''
    -1.26
     recently
    -1.21
     to
    -1.20
     tevreden
    -1.17
     recentes
    -1.16
     moeili
    -1.13
     totalité
    -1.12
    POSITIVE LOGITS
    пло
    1.33
    mohon
    1.26
    பெ
    1.23
     It
    1.21
    mathrm
    1.19
    apeno
    1.17
    ll
    1.16
     Жен
    1.15
    onuclear
    1.14
     وت
    1.11
    Activations Density 0.052%

    No Known Activations