© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33781
    Prev
    Next
    INDEX
    Explanations

    tech brand 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
     Apple
    -1.40
     APPLE
    -1.32
    Apple
    -1.32
    APPLE
    -1.31
    苹果
    -1.26
     apples
    -1.25
    apple
    -1.24
     apple
    -1.22
     Apples
    -1.17
    蘋果
    -1.17
    POSITIVE LOGITS
     Android
    1.44
    Android
    1.19
     Google
    1.11
     android
    1.11
     Windows
    1.08
    Google
    0.99
     Samsung
    0.93
     Linux
    0.92
    android
    0.89
    Windows
    0.87
    Activations Density 0.033%

    No Known Activations