© 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. 123864
    Prev
    Next
    INDEX
    Explanations

    theme song, solar energy, SAT model, town situated, MVC Ajax

    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
     if
    -2.66
     at
    -2.08
     on
    -2.06
     until
    -1.91
     further
    -1.90
     more
    -1.87
     directly
    -1.80
     using
    -1.80
     without
    -1.80
     by
    -1.77
    POSITIVE LOGITS
     tantôt
    1.98
     Inſ
    1.88
     ſou
    1.84
    硨
    1.82
     mauva
    1.80
     soudain
    1.80
     quelquefois
    1.80
     gewi
    1.77
     pauv
    1.76
     bascul
    1.73
    Activations Density 0.197%

    No Known Activations