© 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. 34-GEMMASCOPE-RES-131K
    4. 33073
    Prev
    Next
    INDEX
    Explanations

    if statement

    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_34/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
    aning
    -1.27
     hendes
    -1.23
    iramente
    -1.23
     každého
    -1.23
    šas
    -1.19
     Verkä
    -1.17
    therners
    -1.17
    платье
    -1.17
    Quanto
    -1.16
    Läs
    -1.15
    POSITIVE LOGITS
     there
    3.91
     it
    2.75
     not
    2.33
     we
    2.31
     no
    2.16
     they
    1.78
    there
    1.66
     already
    1.65
     didn
    1.63
     theres
    1.63
    Activations Density 0.088%

    No Known Activations