© 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. 84546
    Prev
    Next
    INDEX
    Explanations

    email addresses, code, non-english words

    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
     inaug
    -0.91
     jurisdic
    -0.91
     despi
    -0.89
     weib
    -0.88
     navidad
    -0.87
     espoir
    -0.86
     imperf
    -0.86
     детских
    -0.85
     kling
    -0.84
     المصري
    -0.84
    POSITIVE LOGITS
     unseren
    0.88
    INK
    0.87
     unserer
    0.86
    ™
    0.84
     comenz
    0.84
     Enhance
    0.83
     azioni
    0.83
     comienza
    0.82
     нашей
    0.82
    artista
    0.82
    Activations Density 0.077%

    No Known Activations