© 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. 12894
    Prev
    Next
    INDEX
    Explanations

    bankruptcy citations

    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
     while
    -0.93
     disadvantaged
    -0.91
     even
    -0.89
     now
    -0.85
    {'
    -0.84
     Spisak
    -0.82
    ด้าน
    -0.80
     continuous
    -0.80
    $\
    -0.78
     …
    -0.76
    POSITIVE LOGITS
    "]}
    0.93
     коллек
    0.88
    kole
    0.88
    fortunately
    0.88
    orodos
    0.87
    OLES
    0.86
    ведення
    0.85
    preferably
    0.85
    足够
    0.83
    itário
    0.82
    Activations Density 0.002%

    No Known Activations