© 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. 10-GEMMASCOPE-RES-131K
    7. 12326
    Prev
    Next
    INDEX
    Explanations

    prefixes from various languages or contexts

    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_10/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
     They
    -2.95
    er
    -2.80
    a
    -2.55
    ↵
    -2.41
    “,
    -2.38
     következő
    -2.34
     dibandingkan
    -2.31
    L
    -2.31
     cię
    -2.30
    s
    -2.27
    POSITIVE LOGITS
                    
    2.38
    delà
    2.28
    盌
    2.27
     魅力
    2.16
     are
    2.14
    ]$.
    2.13
    eſ
    2.09
     was
    2.08
     they
    2.02
    髎
    2.00
    Activations Density 0.000%

    No Known Activations