© 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. 103933
    Prev
    Next
    INDEX
    Explanations

    place names and dates

    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
     Lel
    -0.74
    érat
    -0.74
    ActionPerformed
    -0.72
     खरी
    -0.70
    岡山
    -0.70
    dá
    -0.69
    cadeira
    -0.69
     letting
    -0.68
     Haut
    -0.68
    poietic
    -0.68
    POSITIVE LOGITS
     Benin
    1.24
     Edo
    1.21
    gie
    0.84
    ẹ
    0.82
    vb
    0.79
    jie
    0.79
    osa
    0.76
    Edo
    0.75
    тье
    0.73
     Pendant
    0.72
    Activations Density 0.022%

    No Known Activations