© 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. 1331
    Prev
    Next
    INDEX
    Explanations

    dates, specific groups, or substance use

    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
    未完
    -1.46
    batterie
    -1.37
     increases
    -1.29
    痦
    -1.27
    了一些
    -1.27
    Gön
    -1.23
    珰
    -1.23
    the
    -1.22
    祧
    -1.22
    觏
    -1.21
    POSITIVE LOGITS
     préféré
    1.38
    朱印
    1.36
    妧
    1.35
    íses
    1.35
    鶿
    1.34
     málo
    1.30
    到的
    1.30
     lidé
    1.29
    ︕
    1.28
    说
    1.24
    Activations Density 0.066%

    No Known Activations