© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129802
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns

    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
    </strong>
    -2.80
     Their
    -2.64
     you
    -2.53
    ：
    -2.48
    </u>
    -2.38
    dė
    -2.20
     großen
    -2.19
     meisten
    -2.16
    一直
    -2.16
    ):
    -2.16
    POSITIVE LOGITS
     撮っ
    2.50
    槼
    2.44
    izze
    2.27
    represents
    2.23
    
    2.20
    櫺
    2.19
    ᵴ
    2.16
    鲼
    2.14
    嘥
    2.14
    cant
    2.14
    Activations Density 0.007%

    No Known Activations