© 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. 70453
    Prev
    Next
    INDEX
    Explanations

    ever so, ever since, ever more

    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
     dando
    -3.34
    翕
    -3.13
    \
    -3.02
    
    -2.98
     MAKES
    -2.97
     nè
    -2.89
    
    -2.89
    瘣
    -2.83
    崤
    -2.80
     MEANS
    -2.78
    POSITIVE LOGITS
    There
    3.83
     Surprisingly
    3.58
    After
    3.31
     Even
    3.31
    Although
    3.25
    Despite
    3.20
    When
    3.13
    Surprisingly
    3.11
    Some
    3.11
     There
    3.05
    Activations Density 0.014%

    No Known Activations