© 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. 69561
    Prev
    Next
    INDEX
    Explanations

    prevention of

    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
    }
    -3.28
     was
    -2.94
    )
    -2.69
    ]
    -2.69
    or
    -2.61
    (
    -2.45
    輕鬆
    -2.38
    とき
    -2.34
    個人的には
    -2.31
    다
    -2.28
    POSITIVE LOGITS
    ⽌
    3.11
    ᕱ
    2.86
    虓
    2.72
    狁
    2.67
    聍
    2.67
    ጮ
    2.64
    gée
    2.53
    蘩
    2.52
     Ciebie
    2.50
    袮
    2.44
    Activations Density 0.017%

    No Known Activations