© 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. 54141
    Prev
    Next
    INDEX
    Explanations

    movement followed by direction

    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
    無し
    -1.16
    口
    -1.02
     Something
    -0.98
     esiste
    -0.98
     قب
    -0.93
    ParallelGroup
    -0.91
     lebte
    -0.90
     Kaisers
    -0.90
    mml
    -0.89
    b
    -0.88
    POSITIVE LOGITS
     to
    1.63
     around
    1.38
     through
    1.30
     along
    1.21
     in
    1.16
     down
    1.00
     trails
    0.99
     or
    0.98
     histó
    0.97
     herido
    0.97
    Activations Density 0.019%

    No Known Activations