© 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. 9784
    Prev
    Next
    INDEX
    Explanations

    common phrases or concepts

    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
     dedicata
    -1.06
    жные
    -1.06
    我が
    -1.05
     ricca
    -1.01
    Tento
    -1.01
    信じ
    -1.01
    と言って
    -1.01
     and
    -1.00
     sicura
    -0.99
    艫
    -0.97
    POSITIVE LOGITS
     />
    1.10
     esque
    1.06
    </sup>
    1.05
    tionally
    1.03
    的に
    1.02
    zelf
    1.02
     approach
    0.99
    Notation
    0.98
    йка
    0.97
    abstractmethod
    0.96
    Activations Density 0.070%

    No Known Activations