© 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. 101758
    Prev
    Next
    INDEX
    Explanations

    default values or conditions

    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
     Perhaps
    -1.45
    Otra
    -1.30
     Additionally
    -1.27
    なんですね
    -1.27
    อีก
    -1.27
     cocinar
    -1.26
    Nuestro
    -1.25
    </strong>
    -1.23
    Existen
    -1.23
    Perhaps
    -1.20
    POSITIVE LOGITS
    unless
    1.37
    .»
    1.24
     diu
    1.23
     tenda
    1.20
    or
    1.18
     الاخ
    1.17
     ￥
    1.16
     kela
    1.16
     jaya
    1.16
     uji
    1.15
    Activations Density 0.026%

    No Known Activations