© 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. 34-GEMMASCOPE-RES-131K
    7. 108376
    Prev
    Next
    INDEX
    Explanations

    proper nouns and phrases

    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_34/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
     modalités
    -0.77
    Fuzzy
    -0.74
     Collie
    -0.74
     fumes
    -0.73
    แส
    -0.72
    ucous
    -0.72
    っこう
    -0.71
    PROOF
    -0.69
     ironing
    -0.69
     barter
    -0.69
    POSITIVE LOGITS
     perplex
    1.11
     surpris
    0.81
    ppl
    0.81
    困惑
    0.80
     predictive
    0.80
     poetry
    0.79
     next
    0.78
    lm
    0.78
     anticip
    0.77
     fiction
    0.77
    Activations Density 0.014%

    No Known Activations