© 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. 42499
    Prev
    Next
    INDEX
    Explanations

    seaside and flats

    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
    髕
    -3.11
    薜
    -2.81
    艫
    -2.75
    阋
    -2.69
    潆
    -2.67
    ⸫
    -2.64
    ⃠
    -2.61
    葑
    -2.59
    辚
    -2.58
    潾
    -2.56
    POSITIVE LOGITS
    $
    3.20
     
    3.02
    ↵↵
    2.94
     I
    2.94
    )
    2.77
    E
    2.73
     Also
    2.72
    A
    2.70
    {
    2.56
    We
    2.45
    Activations Density 0.002%

    No Known Activations