© 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. 87398
    Prev
    Next
    INDEX
    Explanations

    event dates and descriptions

    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
     their
    -1.47
     réessayer
    -1.44
     primeras
    -1.42
    therosclerosis
    -1.36
     purpose
    -1.31
     clínica
    -1.30
    spannung
    -1.30
    NewUser
    -1.28
     immedi
    -1.27
     welchen
    -1.27
    POSITIVE LOGITS
     you
    1.58
     bahwa
    1.34
     same
    1.30
    啧
    1.27
     we
    1.25
    restler
    1.23
    信息
    1.20
    \}}
    1.18
     nasional
    1.18
     drei
    1.18
    Activations Density 0.012%

    No Known Activations