© 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. 73452
    Prev
    Next
    INDEX
    Explanations

    not ideal, not pleasant

    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
     goofy
    -1.05
     quirky
    -1.00
     оформление
    -0.95
     unbelievably
    -0.95
     absurd
    -0.93
    报记者
    -0.92
     ridiculously
    -0.91
     amazingly
    -0.90
    keted
    -0.90
    chene
    -0.88
    POSITIVE LOGITS
     pleasant
    1.92
     good
    1.37
     desirable
    1.27
     conducive
    1.19
     ideal
    1.17
    pleasant
    1.12
     optimal
    1.10
     favorable
    1.09
     прият
    1.09
     særlig
    1.06
    Activations Density 0.061%

    No Known Activations