© 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. 99658
    Prev
    Next
    INDEX
    Explanations

    resource extraction and industrial projects

    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
    fucker
    -1.20
     Enquanto
    -1.19
    ꧁
    -1.18
    ſo
    -1.17
    niña
    -1.16
    activer
    -1.13
    קד
    -1.12
    Étienne
    -1.12
     restant
    -1.10
     urch
    -1.09
    POSITIVE LOGITS
     it
    1.55
     new
    1.32
     "
    1.16
     aquí
    1.16
     очень
    1.15
     möchte
    1.14
    他和
    1.13
    zsef
    1.10
     один
    1.10
     ["
    1.10
    Activations Density 0.085%

    No Known Activations