© 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. 87119
    Prev
    Next
    INDEX
    Explanations

    stealing data, Islam, Predisposing factors

    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
    länger
    -0.93
     Inglaterra
    -0.92
     todav
    -0.92
    samt
    -0.90
     avoiding
    -0.89
     Menggunakan
    -0.87
     information
    -0.86
    Mikhail
    -0.85
    heizung
    -0.85
     Though
    -0.85
    POSITIVE LOGITS
    ");
    1.04
     pivotal
    0.91
    ąp
    0.87
     blessures
    0.84
    📠
    0.84
     कि
    0.83
    INI
    0.82
    still
    0.82
    ⋮
    0.81
    DOI
    0.81
    Activations Density 0.000%

    No Known Activations