© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77598
    Prev
    Next
    INDEX
    Explanations

    foam and bubbles

    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
     لاعب
    -0.73
     fichiers
    -0.73
    лади
    -0.73
    ophyllum
    -0.72
     Trenton
    -0.68
     FLEX
    -0.68
    DrawerToggle
    -0.67
    的气息
    -0.67
    zieren
    -0.66
     أهل
    -0.66
    POSITIVE LOGITS
     foam
    4.00
     Foam
    3.13
    Foam
    2.84
    foam
    2.81
     foaming
    2.55
     fro
    2.52
     foams
    2.47
     espuma
    2.41
     bubbles
    2.25
    泡沫
    2.00
    Activations Density 0.034%

    No Known Activations