© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 87169
    Prev
    Next
    INDEX
    Explanations

    pronouns (he, she, his, him, her, me)

    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
     of
    -1.80
     muhimu
    -1.57
     zrobić
    -1.27
    它
    -1.23
     TECHNIQUES
    -1.21
     vertus
    -1.20
     rumput
    -1.20
     ISSUED
    -1.20
    utched
    -1.20
     TECH
    -1.20
    POSITIVE LOGITS
     our
    2.22
     only
    1.59
    蒞
    1.47
    ׇ
    1.41
     doar
    1.41
    Our
    1.37
    Only
    1.35
     Our
    1.34
     nosso
    1.32
     nossas
    1.30
    Activations Density 0.093%

    No Known Activations