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. 8740
    Prev
    Next
    INDEX
    Explanations

    adult patients introduction

    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
     would
    -1.04
     any
    -0.85
     even
    -0.79
     keeps
    -0.76
     found
    -0.76
     Aleksander
    -0.75
     after
    -0.75
     gets
    -0.75
     did
    -0.74
     Hoss
    -0.74
    POSITIVE LOGITS
    きち
    0.92
    )),
    0.90
    türk
    0.88
    JMenu
    0.84
    remain
    0.82
    >,</
    0.81
    contain
    0.81
    still
    0.81
     intertw
    0.78
    StatusBadRequest
    0.77
    Activations Density 0.001%

    No Known Activations