© 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. 22-GEMMASCOPE-RES-131K
    7. 15364
    Prev
    Next
    INDEX
    Explanations

    listing diverse items in a sentence

    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
     autres
    -1.42
     other
    -1.37
     innych
    -1.16
     diğer
    -1.15
     andere
    -1.10
     otras
    -1.06
     demás
    -1.02
     lainnya
    -1.01
     autre
    -1.00
     outras
    -1.00
    POSITIVE LOGITS
     including
    1.28
    包括
    1.20
    including
    1.12
     sogar
    0.99
     addirittura
    0.95
    Including
    0.94
     jedoch
    0.93
     atardecer
    0.92
     include
    0.91
     však
    0.89
    Activations Density 0.162%

    No Known Activations