© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 32513
    Prev
    Next
    INDEX
    Explanations

    l as a prefix or standalone

    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
    iu
    -1.00
    闔
    -0.90
    ige
    -0.90
    iet
    -0.85
    ниці
    -0.83
    acd
    -0.82
    acyl
    -0.81
    érc
    -0.81
    wii
    -0.81
    am
    -0.80
    POSITIVE LOGITS
     l
    0.99
    公式サイト
    0.93
    visible
    0.91
    ビ
    0.89
    中古
    0.88
    ・・・・
    0.85
    sort
    0.85
     complètement
    0.84
    please
    0.83
    容易
    0.83
    Activations Density 0.017%

    No Known Activations