© 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. 85124
    Prev
    Next
    INDEX
    Explanations

    application.service

    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
     chré
    -1.45
     religieuses
    -1.38
    emed
    -1.31
     then
    -1.28
     曲
    -1.20
     veckor
    -1.20
     Escribe
    -1.19
     maxY
    -1.18
     söyl
    -1.16
    faits
    -1.15
    POSITIVE LOGITS
    Beschrijving
    1.44
    Descriere
    1.41
    Beskrivelse
    1.33
    urilor
    1.32
    ྱ
    1.31
    cellona
    1.24
     vermelhas
    1.23
    andidat
    1.21
    jetivo
    1.21
    ]/
    1.21
    Activations Density 0.049%

    No Known Activations