© 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. 123598
    Prev
    Next
    INDEX
    Explanations

    confusion or confused

    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
    𖣘
    -2.75
    )
    -2.70
    鉭
    -2.66
     desideri
    -2.61
    );
    -2.56
     dimentic
    -2.55
    這個
    -2.52
    튿
    -2.48
     riservata
    -2.48
    ));
    -2.48
    POSITIVE LOGITS
    .
    4.72
    とはいえ
    2.25
    相性
    2.19
    ↵
    2.19
    欉
    2.13
    ጵ
    2.09
    熜
    2.05
    GRAND
    2.03
    别人
    2.02
     животные
    2.02
    Activations Density 0.004%

    No Known Activations