© 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. 34572
    Prev
    Next
    INDEX
    Explanations

    common programming variable names

    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
     ônibus
    -1.13
     PLAYING
    -1.06
     sabias
    -1.05
     cavalo
    -1.01
    hishek
    -0.98
    irii
    -0.97
    Cliquez
    -0.96
    ⇴
    -0.96
    hieu
    -0.96
    jata
    -0.96
    POSITIVE LOGITS
    L
    1.02
    g
    1.02
    ch
    1.02
    h
    0.99
    ent
    0.97
    si
    0.96
    ian
    0.96
    k
    0.95
    ph
    0.93
    c
    0.93
    Activations Density 0.019%

    No Known Activations