© 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. 915
    Prev
    Next
    INDEX
    Explanations

    ----- followed by email metadata

    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
     use
    -2.31
     will
    -1.98
    ?
    -1.96
     always
    -1.90
    =
    -1.89
     -
    -1.80
    常用的
    -1.76
     this
    -1.74
     immediate
    -1.69
     .
    -1.67
    POSITIVE LOGITS
    踅
    1.95
     実例
    1.91
     londres
    1.89
     不锈钢
    1.87
     menyen
    1.84
     rigue
    1.78
    镦
    1.78
    ꜆
    1.76
     unſ
    1.75
     både
    1.74
    Activations Density 0.034%

    No Known Activations