© 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. 34-GEMMASCOPE-RES-131K
    7. 25633
    Prev
    Next
    INDEX
    Explanations

    interpreting or resolving text

    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_34/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
     Lotion
    -0.90
    }=-\
    -0.83
    tamol
    -0.82
     evidently
    -0.81
    精准
    -0.78
    Slf
    -0.78
     impeccable
    -0.77
    Lịch
    -0.77
    Magyar
    -0.76
     seems
    -0.75
    POSITIVE LOGITS
     liberally
    1.32
     construed
    1.32
     view
    1.12
    view
    1.09
     resolving
    1.03
    constr
    1.02
     constr
    0.99
    View
    0.98
    VIEW
    0.91
     viewing
    0.90
    Activations Density 0.028%

    No Known Activations