© 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. 70346
    Prev
    Next
    INDEX
    Explanations

    col prefix

    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
    ﹶ
    -2.16
    膈
    -1.82
     ,‬
    -1.66
    )=>{
    -1.62
     ビーチ
    -1.61
    谞
    -1.61
    }
    -1.56
     婚礼
    -1.55
    人事
    -1.52
    ﹑
    -1.48
    POSITIVE LOGITS
    0
    1.97
    3
    1.92
    1
    1.79
    急に
    1.78
    )
    1.75
    9
    1.73
     "...
    1.71
    私は
    1.69
    _
    1.61
    相変わらず
    1.59
    Activations Density 0.007%

    No Known Activations