© 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. 22-GEMMASCOPE-RES-131K
    7. 12465
    Prev
    Next
    INDEX
    Explanations

    determiner followed by descriptive word

    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_22/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
    関連リンク
    -1.31
     bereits
    -1.18
    }(),
    -1.13
    ຣ
    -1.13
     that
    -1.13
    を選択します
    -1.10
    入る
    -1.09
    éroport
    -1.09
    おわりに
    -1.09
    到时候
    -1.09
    POSITIVE LOGITS
     his
    1.32
    窺
    1.05
     suoi
    1.05
     at
    1.04
     comedia
    1.03
     œil
    1.03
     caricatura
    1.02
    AYS
    1.01
     grotte
    1.01
    他
    1.00
    Activations Density 0.000%

    No Known Activations