© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73952
    Prev
    Next
    INDEX
    Explanations

    overlying plasma, whose motto, low oil, sounds stadium, multi-drug

    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
    ’
    -2.38
    er
    -2.17
    ");
    -2.16
    an
    -2.00
     スケ
    -1.96
    榈
    -1.95
    strator
    -1.88
    劒
    -1.84
     imprescin
    -1.84
    anthene
    -1.83
    POSITIVE LOGITS
    了啊
    2.19
    很赞
    2.16
     Those
    2.09
    
    2.05
     It
    1.95
    此前
    1.94
    いわゆる
    1.94
    真好
    1.90
     intricacies
    1.88
     Numerous
    1.83
    Activations Density 0.000%

    No Known Activations