© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84028
    Prev
    Next
    INDEX
    Explanations

    attributes of things

    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
     แต่
    -1.28
     nggak
    -1.13
     tetapi
    -1.10
    と思いますが
    -1.04
    ごく
    -1.02
     presentará
    -0.99
    のですが
    -0.99
     exprim
    -0.98
     volverá
    -0.98
     REALLY
    -0.98
    POSITIVE LOGITS
     appellee
    0.98
    For
    0.96
     invece
    0.93
     use
    0.92
    有问题
    0.91
    ativement
    0.91
    ⬆
    0.90
    ι
    0.89
     and
    0.89
    yya
    0.89
    Activations Density 0.075%

    No Known Activations