© 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. 10-GEMMASCOPE-RES-131K
    7. 21852
    Prev
    Next
    INDEX
    Explanations

    movement and 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_10/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
     when
    -2.41
    ቍ
    -1.84
     it
    -1.82
    🢒
    -1.79
     untuk
    -1.78
     ledig
    -1.78
     a
    -1.70
    .(*
    -1.70
     after
    -1.67
     после
    -1.59
    POSITIVE LOGITS
     into
    3.63
     onto
    2.47
     away
    2.42
     down
    2.39
     to
    2.25
     out
    2.08
     up
    2.03
     其他
    1.88
     towards
    1.88
     toward
    1.84
    Activations Density 0.201%

    No Known Activations