© 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. 34-GEMMASCOPE-RES-131K
    7. 116506
    Prev
    Next
    INDEX
    Explanations

    all-preceding descriptive words

    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_34/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
    了一個
    -0.92
    拍了拍
    -0.89
    lization
    -0.85
    atious
    -0.84
    atization
    -0.83
    した場合
    -0.82
    OLOGIES
    -0.81
    了什么
    -0.81
    争取
    -0.81
     erity
    -0.81
    POSITIVE LOGITS
     pure
    1.17
     entirely
    1.05
     black
    1.04
     国道
    1.02
     white
    0.97
     female
    0.96
     one
    0.96
     blue
    0.94
     different
    0.93
     green
    0.88
    Activations Density 0.052%

    No Known Activations