© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110433
    Prev
    Next
    INDEX
    Explanations

    SPDX license identifiers

    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
    Sabes
    -0.88
     Monats
    -0.86
    
    -0.86
    Zobacz
    -0.85
     Acht
    -0.84
    beginTransaction
    -0.83
     principles
    -0.83
     Wege
    -0.82
    lancer
    -0.80
    革
    -0.79
    POSITIVE LOGITS
     нужны
    0.82
    Huile
    0.81
     solidity
    0.81
     SPDX
    0.80
    Torna
    0.79
    嗆
    0.77
     explicó
    0.76
    好吃的
    0.76
    ohistochemistry
    0.75
    Aspen
    0.74
    Activations Density 0.053%

    No Known Activations