© 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. 110866
    Prev
    Next
    INDEX
    Explanations

    downright phony awful

    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
    Awesome
    -1.11
     Awesome
    -1.08
     spreadsheet
    -1.05
     шампу
    -1.04
    Dude
    -1.03
     реально
    -1.02
    Clearly
    -1.01
     über
    -1.01
     clairement
    -1.01
    awesome
    -1.00
    POSITIVE LOGITS
     phony
    1.04
     queer
    0.97
     contesta
    0.94
     awfully
    0.93
     downright
    0.92
     Queer
    0.92
     plenty
    0.90
    dope
    0.90
     goddamn
    0.87
     lousy
    0.87
    Activations Density 0.047%

    No Known Activations