© 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. 3720
    Prev
    Next
    INDEX
    Explanations

    ships and naval vessels

    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
     simila
    -1.50
    geladen
    -1.41
    forcing
    -1.35
    детская
    -1.34
    য
    -1.32
     ESPEC
    -1.31
    毟
    -1.30
    Activités
    -1.27
     píše
    -1.27
     beleid
    -1.27
    POSITIVE LOGITS
     by
    2.02
     from
    1.85
     if
    1.81
     even
    1.68
     several
    1.51
     without
    1.43
     four
    1.42
     had
    1.41
     any
    1.36
     have
    1.34
    Activations Density 0.054%

    No Known Activations