© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38621
    Prev
    Next
    INDEX
    Explanations

    social organization and society

    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
    鸶
    -3.55
    亖
    -3.47
    埽
    -2.92
    ⚢
    -2.91
    俛
    -2.88
    鲞
    -2.83
    滹
    -2.81
    佉
    -2.81
    梘
    -2.81
    毉
    -2.80
    POSITIVE LOGITS
    t
    3.16
    ]
    3.06
    }
    2.78
    {
    2.75
    c
    2.56
    硯
    2.55
    /
    2.53
    f
    2.52
    %
    2.50
    施工
    2.44
    Activations Density 0.009%

    No Known Activations