© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54446
    Prev
    Next
    INDEX
    Explanations

    code comments and conditional statements

    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_22/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
     tragedia
    -1.15
     emblema
    -1.10
     pilotes
    -1.06
    																															
    -1.06
     adverten
    -1.05
     Kartu
    -1.05
    んだろう
    -1.05
     pittores
    -1.04
     palav
    -1.03
    [:,:,
    -1.02
    POSITIVE LOGITS
    --
    1.03
    //
    0.95
    5
    0.95
    if
    0.94
    通过
    0.93
    4
    0.93
    ...
    0.91
    0
    0.91
    i
    0.89
    o
    0.88
    Activations Density 0.001%

    No Known Activations