© 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. 65710
    Prev
    Next
    INDEX
    Explanations

    short clothing and body parts

    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
    缓慢
    -1.37
     morrer
    -1.35
    caccio
    -1.30
     éviter
    -1.27
    自由に
    -1.26
    ]
    -1.24
    胧
    -1.23
    .
    -1.22
     proib
    -1.22
     mour
    -1.22
    POSITIVE LOGITS
     短
    1.49
    短
    1.48
    女
    1.43
    又
    1.38
     Short
    1.30
    z
    1.29
     wouldn
    1.27
    1
    1.27
    只
    1.24
     ショート
    1.23
    Activations Density 0.068%

    No Known Activations