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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6740
    Prev
    Next
    INDEX
    Explanations

    script headers and comments

    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
     recently
    -1.16
     any
    -1.13
     irrespective
    -1.09
     Recently
    -1.09
     Depending
    -1.04
     recent
    -1.02
     after
    -1.02
     very
    -0.98
     has
    -0.98
     sizeable
    -0.97
    POSITIVE LOGITS
     deaktiviert
    1.06
     verschillende
    1.00
     aktiviert
    0.97
     stehenden
    0.96
     finalement
    0.95
     общего
    0.94
     két
    0.94
    για
    0.93
     gebruiken
    0.93
    Writing
    0.91
    Activations Density 0.012%

    No Known Activations