© 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. 22-GEMMASCOPE-RES-131K
    4. 71635
    Prev
    Next
    INDEX
    Explanations

    android fragment lifecycle

    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
     illustrationer
    -1.10
     enfrentan
    -1.05
     lavadora
    -1.02
    皈
    -1.02
    riors
    -1.00
     Philosophie
    -0.99
     传统
    -0.99
     洛
    -0.99
    boa
    -0.98
    saveButton
    -0.96
    POSITIVE LOGITS
    ünsche
    1.03
    hadap
    1.02
    Хороший
    1.01
    AMENTO
    0.96
     çağ
    0.94
    พอ
    0.94
    gucig
    0.93
    QUET
    0.91
    評判
    0.91
    kwargs
    0.91
    Activations Density 0.008%

    No Known Activations