© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44129
    Prev
    Next
    INDEX
    Explanations

    prefixes, initials, or abbreviations

    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
     doesnt
    -2.69
    
    -2.53
    珰
    -2.52
    ?
    -2.47
    孓
    -2.42
    婞
    -2.41
     '
    -2.36
     conglomerate
    -2.34
    "'
    -2.33
    有助
    -2.33
    POSITIVE LOGITS
     Technically
    3.03
     But
    2.72
     Surprisingly
    2.63
     Notably
    2.59
     Traditionally
    2.52
    鹀
    2.47
     雙
    2.45
     After
    2.44
    On
    2.41
     Subsequently
    2.41
    Activations Density 0.000%

    No Known Activations