© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14279
    Prev
    Next
    INDEX
    Explanations

    code snippets and data structures

    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
    辂
    -1.45
    URLEncoder
    -1.41
     ↓,
    -1.39
     savon
    -1.39
     maire
    -1.33
    lovely
    -1.32
     <<<<<<<<<<<<<<
    -1.31
     ffilm
    -1.30
    leopard
    -1.28
    nemone
    -1.25
    POSITIVE LOGITS
    According
    1.77
    Because
    1.77
     specific
    1.76
    They
    1.72
     According
    1.71
     particular
    1.64
     Because
    1.52
    These
    1.52
     specifically
    1.52
     attuale
    1.50
    Activations Density 0.044%

    No Known Activations