© 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. 118600
    Prev
    Next
    INDEX
    Explanations

    Android lifecycle methods

    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
    Cope
    -0.83
    :{
    -0.81
    lendi
    -0.80
     contorno
    -0.79
    申し
    -0.79
    idings
    -0.79
    க்கு
    -0.79
     ancienne
    -0.79
    ciun
    -0.79
     toneladas
    -0.78
    POSITIVE LOGITS
     onResume
    1.15
     resume
    1.10
     resumed
    1.02
     resumes
    0.91
    override
    0.88
    resume
    0.87
     pause
    0.81
     viewWillAppear
    0.81
    Resume
    0.81
     resuming
    0.80
    Activations Density 0.005%

    No Known Activations