© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59054
    Prev
    Next
    INDEX
    Explanations

    HTTP URLs, code blocks, or specific phrases

    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
     crossorigin
    -1.25
     artistas
    -1.07
     memili
    -1.06
     доставки
    -1.05
    ๒
    -1.03
     või
    -1.02
    <0xF0>
    -0.99
     ako
    -0.98
    之色
    -0.95
    ฿
    -0.95
    POSITIVE LOGITS
    >
    1.34
     dachshund
    1.08
     maint
    1.02
     betreffende
    1.02
     tyran
    1.02
     supplementing
    1.02
     rhinoceros
    1.02
     zweimal
    1.02
     esquerdo
    1.00
     cougar
    0.98
    Activations Density 0.000%

    No Known Activations