© 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. 48320
    Prev
    Next
    INDEX
    Explanations

    android os package

    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
     июня
    -0.87
    ようになります
    -0.82
    Cadastro
    -0.78
    appcompat
    -0.77
    常に
    -0.77
    requestData
    -0.76
    京东
    -0.75
     ersetzt
    -0.75
    グリップ
    -0.74
     getKey
    -0.74
    POSITIVE LOGITS
     Tablet
    0.85
    Tablet
    0.82
     binder
    0.82
     וו
    0.80
    苛
    0.77
    tablet
    0.77
     fontWeight
    0.75
    榛
    0.73
    ódó
    0.73
     Remote
    0.72
    Activations Density 0.002%

    No Known Activations