© 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. 50017
    Prev
    Next
    INDEX
    Explanations

    I like the / I love the

    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
     juiste
    -1.34
     keindahan
    -1.06
     loveliness
    -1.04
     prachtig
    -1.03
     kepentingan
    -1.02
     регулярно
    -1.02
     pikiran
    -1.02
     keinginan
    -0.99
     verkoop
    -0.99
     penghargaan
    -0.97
    POSITIVE LOGITS
     idea
    2.47
     way
    2.06
     concept
    1.95
     fact
    1.84
    idea
    1.82
     smell
    1.52
     simplicity
    1.52
     vibe
    1.49
     look
    1.48
     approach
    1.42
    Activations Density 0.029%

    No Known Activations