Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8656
    Prev
    Next
    INDEX
    Explanations

    protecting items with sleeves or covers

    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
    lle
    -0.84
     drapes
    -0.75
     櫻
    -0.74
    طة
    -0.73
    siyon
    -0.73
     paraffin
    -0.71
    rative
    -0.71
     Clive
    -0.71
    lons
    -0.71
    illez
    -0.70
    POSITIVE LOGITS
     sleeved
    1.04
     protective
    1.01
    sleeve
    0.99
     sleeves
    0.97
     protection
    0.94
     sleeve
    0.93
     protecting
    0.91
     Protective
    0.89
     bending
    0.88
    Sleeve
    0.87
    Activations Density 0.012%

    No Known Activations