© 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. 73693
    Prev
    Next
    INDEX
    Explanations

    android id

    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
     kopling
    -1.04
    quê
    -1.03
     ilma
    -0.98
     lyder
    -0.97
    cuba
    -0.96
    тео
    -0.96
     ciebie
    -0.93
     integrante
    -0.91
     procurando
    -0.91
    andafter
    -0.90
    POSITIVE LOGITS
     radio
    1.14
    ID
    1.10
    p
    0.96
    rb
    0.96
    bt
    0.95
    b
    0.94
     radios
    0.94
    cb
    0.94
     Radio
    0.94
    id
    0.93
    Activations Density 0.001%

    No Known Activations