© 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. 22-GEMMASCOPE-RES-131K
    7. 13146
    Prev
    Next
    INDEX
    Explanations

    android layout attributes

    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_22/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
     to
    -1.05
    CURLOPT
    -1.01
    OSO
    -1.00
     nuove
    -0.98
     its
    -0.95
     their
    -0.94
    nicity
    -0.91
    tikal
    -0.90
    その
    -0.88
     inicia
    -0.88
    POSITIVE LOGITS
     also
    1.10
    可能會
    0.97
    这一切
    0.96
    Ӏ
    0.95
    机遇
    0.93
    就可以了
    0.93
    ええ
    0.92
     Porte
    0.92
     anillos
    0.91
     نیز
    0.91
    Activations Density 0.001%

    No Known Activations