© 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. 4198
    Prev
    Next
    INDEX
    Explanations

    describing unpleasant qualities

    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
     delicioso
    -1.00
    itement
    -0.98
     مفید
    -0.97
    moderate
    -0.97
    ņš
    -0.95
     nien
    -0.94
     miſ
    -0.93
    mability
    -0.93
     masas
    -0.93
    皷
    -0.93
    POSITIVE LOGITS
     oily
    1.29
     sticky
    1.05
     noisy
    1.05
     buggy
    1.00
    有很多
    0.95
     woody
    0.94
     sloppy
    0.90
     has
    0.90
     windy
    0.89
     foggy
    0.89
    Activations Density 0.052%

    No Known Activations