© 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. 22-GEMMASCOPE-RES-131K
    7. 73704
    Prev
    Next
    INDEX
    Explanations

    repeated actions

    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_22/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
     ersten
    -1.02
     obecnie
    -0.96
     никогда
    -0.96
     these
    -0.96
    adalah
    -0.95
    Both
    -0.93
    ↵
    -0.93
     introductory
    -0.92
     both
    -0.91
     solcher
    -0.90
    POSITIVE LOGITS
     again
    5.09
     further
    3.63
    again
    3.47
    Again
    3.14
     Again
    2.94
     AGAIN
    2.91
     erneut
    2.78
    再び
    2.67
     continued
    2.63
    继续
    2.61
    Activations Density 0.036%

    No Known Activations