© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58245
    Prev
    Next
    INDEX
    Explanations

    Utility of, JavaOS, Has July

    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
     puis
    -0.96
    aguay
    -0.89
     Spannung
    -0.87
     powiedzieć
    -0.86
     lalu
    -0.85
     avril
    -0.85
    ulha
    -0.85
     wiedzieć
    -0.83
    dekat
    -0.82
     acoged
    -0.82
    POSITIVE LOGITS
    )　
    1.05
     Nevertheless
    1.05
    ях
    1.02
    newRow
    1.01
     pareti
    0.99
    いれば
    0.98
     msglen
    0.98
     albero
    0.96
     Nonetheless
    0.96
    iasaan
    0.95
    Activations Density 0.000%

    No Known Activations