© 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. 22-GEMMASCOPE-RES-131K
    7. 104545
    Prev
    Next
    INDEX
    Explanations

    often therefore

    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
     it
    -1.29
     only
    -1.09
     hadn
    -0.95
     childhood
    -0.91
     actualmente
    -0.90
     Dependencies
    -0.89
     solamente
    -0.88
     Geol
    -0.88
    だったが
    -0.87
     didn
    -0.84
    POSITIVE LOGITS
     often
    1.58
    Therefore
    1.45
     Therefore
    1.40
    Often
    1.34
    often
    1.32
     často
    1.31
     часто
    1.19
     поэтому
    1.17
     często
    1.16
     både
    1.16
    Activations Density 0.372%

    No Known Activations