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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76854
    Prev
    Next
    INDEX
    Explanations

    android context and application

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags occurrences of programming‐language type or class names (e.g., Context, Application, AttributeSet, View, Bundle, Job).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Files
    -0.86
     antim
    -0.82
    வு
    -0.82
    ਾਈ
    -0.81
     Funds
    -0.79
    Scopes
    -0.77
     الثانية
    -0.75
    基金
    -0.75
     puder
    -0.75
     nationwide
    -0.74
    POSITIVE LOGITS
    手镯
    0.95
     Utilization
    0.81
    Toul
    0.81
     женщина
    0.80
     mukana
    0.77
     context
    0.76
     hatched
    0.75
     ansatte
    0.75
    няться
    0.74
     arbeid
    0.74
    Activations Density 0.019%

    No Known Activations