© 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. 89831
    Prev
    Next
    INDEX
    Explanations

    moving forward

    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
    urora
    -0.90
     desafios
    -0.88
     effectually
    -0.87
     constantemente
    -0.87
    🥅
    -0.85
     remarqué
    -0.84
     arrivant
    -0.83
    EOUT
    -0.82
    τικού
    -0.82
     alkoholu
    -0.82
    POSITIVE LOGITS
     proceed
    3.75
     proceeding
    3.14
     proceeded
    2.88
     pursue
    2.73
    proceed
    2.64
     Proceed
    2.61
     PROCEED
    2.39
    Proceed
    2.38
     proceeds
    2.30
     pursued
    2.09
    Activations Density 0.070%

    No Known Activations