© 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. 23545
    Prev
    Next
    INDEX
    Explanations

    press fit and interference fit

    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
    ibles
    -0.77
    Attach
    -0.73
    Latch
    -0.73
    ьому
    -0.71
    imdb
    -0.71
    coledì
    -0.68
     arcos
    -0.68
    Thickness
    -0.67
    SpringRunner
    -0.67
     paiement
    -0.67
    POSITIVE LOGITS
     press
    2.06
     interference
    2.05
     Interference
    1.76
    interference
    1.75
    press
    1.58
     Press
    1.54
    Press
    1.49
     fit
    1.38
     pressed
    1.38
     presses
    1.31
    Activations Density 0.110%

    No Known Activations