© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75279
    Prev
    Next
    INDEX
    Explanations

    mathematical terms

    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
    }_{\
    -1.29
     iNdEx
    -1.05
    ρού
    -1.05
     trzeba
    -1.03
     ngay
    -1.02
    |_{\
    -1.00
    larak
    -0.99
     бампер
    -0.99
     сможете
    -0.99
    ௌ
    -0.98
    POSITIVE LOGITS
     motocic
    1.11
     eterna
    1.02
     recompensa
    1.00
     comanda
    0.96
     catholique
    0.95
     favoris
    0.94
     Lesnar
    0.93
    })();
    0.92
     Bearbeit
    0.91
     busto
    0.91
    Activations Density 0.063%

    No Known Activations