© 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. 10-GEMMASCOPE-RES-131K
    7. 19604
    Prev
    Next
    INDEX
    Explanations

    approaching the verge of

    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
    .
    -2.31
     “
    -1.59
     принад
    -1.55
     ‘
    -1.52
    =’
    -1.52
    ”:
    -1.52
     “…
    -1.51
    」。
    -1.48
     jugando
    -1.48
    <\
    -1.45
    POSITIVE LOGITS
    钢琴
    1.91
     hoffe
    1.82
    StoryboardSegue
    1.71
    ême
    1.70
    ărat
    1.66
     促销
    1.63
    草莓
    1.52
    寐
    1.52
     becoming
    1.52
    囖
    1.50
    Activations Density 0.012%

    No Known Activations