© 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. 66057
    Prev
    Next
    INDEX
    Explanations

    me, you, us 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
    </b>
    -2.45
    了一个
    -2.39
    そうですが
    -1.90
    2
    -1.88
     як
    -1.84
    </em>
    -1.83
     was
    -1.80
    所谓的
    -1.79
    了两
    -1.76
    并将
    -1.73
    POSITIVE LOGITS
    躥
    2.34
     όταν
    2.06
     través
    2.05
    medriver
    2.03
    輊
    1.98
    ⸥
    1.95
    ㉕
    1.95
    лтемелер
    1.94
     när
    1.94
    『
    1.92
    Activations Density 0.019%

    No Known Activations