© 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. 22-GEMMASCOPE-RES-131K
    7. 79758
    Prev
    Next
    INDEX
    Explanations

    following introductions or statements

    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_22/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
     necesito
    -1.05
    ktar
    -1.03
     плохо
    -0.98
    jalá
    -0.96
    itaji
    -0.95
     souhaitent
    -0.93
     añade
    -0.90
     usando
    -0.88
     anuncia
    -0.87
     takı
    -0.87
    POSITIVE LOGITS
     instead
    1.33
     invece
    1.26
     trotzdem
    1.13
     dennoch
    1.10
     remaining
    1.07
     remain
    1.06
     now
    1.05
     still
    1.05
    Instead
    1.05
    代わりに
    1.01
    Activations Density 0.000%

    No Known Activations