© 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. 48240
    Prev
    Next
    INDEX
    Explanations

    airtight and sealing

    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
     estabiliz
    -0.77
     viejos
    -0.76
     çı
    -0.73
     médicaments
    -0.69
     softening
    -0.69
    Conflicts
    -0.68
    لية
    -0.67
     Fuzz
    -0.66
    Translatef
    -0.66
    Unset
    -0.66
    POSITIVE LOGITS
     sealed
    3.59
     airtight
    3.48
     sealing
    3.08
    sealed
    3.02
     seal
    3.02
     seals
    2.69
     Sealed
    2.58
     гер
    2.50
    seal
    2.47
    Sealed
    2.44
    Activations Density 0.103%

    No Known Activations