© 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. 73030
    Prev
    Next
    INDEX
    Explanations

    email address

    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
     However
    -1.91
    The
    -1.88
     undergone
    -1.74
     ricordo
    -1.70
    ⑉
    -1.66
    錞
    -1.64
     decrease
    -1.59
     двох
    -1.59
    獴
    -1.57
    丏
    -1.57
    POSITIVE LOGITS
    ’
    2.34
    ﹍﹍
    1.98
     группу
    1.88
     („
    1.87
    })}
    1.86
    的主要
    1.84
    “
    1.77
    靫
    1.75
    ʼ
    1.73
    的人
    1.72
    Activations Density 0.007%

    No Known Activations