© 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. 34-GEMMASCOPE-RES-131K
    7. 119265
    Prev
    Next
    INDEX
    Explanations

    languages, Romance, Indo-European

    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
    chers
    -0.84
    pkins
    -0.82
    auro
    -0.77
    huana
    -0.72
    foria
    -0.72
    HomeComponent
    -0.72
    联赛
    -0.71
    tró
    -0.68
    elde
    -0.67
     Lipp
    -0.66
    POSITIVE LOGITS
     Romance
    1.61
    Romance
    1.59
     Indo
    1.33
     languages
    1.31
     romance
    1.26
    Languages
    1.20
     Languages
    1.11
    romance
    1.00
    Indo
    0.99
    languages
    0.98
    Activations Density 0.052%

    No Known Activations