© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10731
    Prev
    Next
    INDEX
    Explanations

    looking up, turned, glanced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     philosoph
    0.99
    philosoph
    0.95
     monologue
    0.92
    黯
    0.89
     Ramb
    0.89
    謨
    0.88
    सू
    0.86
    鑿
    0.85
    决
    0.85
     persuas
    0.85
    POSITIVE LOGITS
     Oviedo
    0.86
     surprise
    0.80
     internacional
    0.80
     evacuated
    0.79
     stag
    0.79
     startled
    0.77
    šk
    0.77
     internasional
    0.74
    international
    0.74
     expats
    0.73
    Activations Density 0.049%

    No Known Activations