© 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. 34-GEMMASCOPE-RES-131K
    7. 2242
    Prev
    Next
    INDEX
    Explanations

    thus introducing explanation

    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
    ."*
    -1.21
    ...",
    -1.20
     цього
    -1.15
     этого
    -1.14
    羈
    -1.09
    
    -1.08
     and
    -1.08
    Смотрите
    -1.07
    
    -1.07
    '."
    -1.06
    POSITIVE LOGITS
     far
    1.92
     began
    1.69
     begins
    1.66
     ends
    1.38
     equipped
    1.34
     facendo
    1.33
     we
    1.31
     it
    1.30
     configured
    1.30
     begin
    1.28
    Activations Density 0.012%

    No Known Activations