© 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. 22-GEMMASCOPE-RES-131K
    7. 84504
    Prev
    Next
    INDEX
    Explanations

    rehearing denied

    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_22/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
    などが
    -1.03
     всички
    -0.99
     appris
    -0.99
     escritório
    -0.99
     теперь
    -0.96
    今は
    -0.95
     Präsidenten
    -0.94
     banheiro
    -0.94
     estrena
    -0.93
     nuevos
    -0.91
    POSITIVE LOGITS
     will
    1.75
     לאחר
    1.13
    慈
    1.07
    妾
    1.04
     legais
    1.02
     spending
    0.97
     IBOutlet
    0.95
     материалам
    0.95
    щет
    0.94
     his
    0.92
    Activations Density 0.000%

    No Known Activations