© 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. 9656
    Prev
    Next
    INDEX
    Explanations

    C-terminal / D-Day / USA

    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
    9
    -2.83
    0
    -2.78
     для
    -2.50
    5
    -2.39
     untuk
    -2.34
     exquisite
    -2.31
    8
    -2.31
    ၟ
    -2.28
    </strong>
    -2.27
     dramatically
    -2.27
    POSITIVE LOGITS
    麁
    2.58
    媵
    2.38
    も含
    2.30
    刄
    2.22
     accentu
    2.20
     diminuer
    2.16
    嗵
    2.13
    鼍
    2.08
    だけではなく
    2.08
    だけでなく
    2.08
    Activations Density 0.075%

    No Known Activations