© 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. 10-GEMMASCOPE-RES-131K
    7. 60124
    Prev
    Next
    INDEX
    Explanations

    within a context

    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_10/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
     Organizador
    -1.52
    still
    -1.48
    Jaunes
    -1.48
     můžete
    -1.39
    纔
    -1.38
     EARLY
    -1.38
     ragioni
    -1.35
     Mejora
    -1.35
    יהם
    -1.35
    嘍
    -1.34
    POSITIVE LOGITS
     it
    1.84
     That
    1.70
     context
    1.66
    </u>
    1.51
     contexto
    1.50
    𝗨
    1.43
     +
    1.42
     more
    1.42
     normas
    1.39
     other
    1.37
    Activations Density 0.046%

    No Known Activations