© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39582
    Prev
    Next
    INDEX
    Explanations

    Bad Bunny, Badgers, Badfinger

    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_10/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
    茀
    -3.25
    
    -2.97
    嵛
    -2.92
    迨
    -2.88
    衚
    -2.84
     lidé
    -2.67
    菹
    -2.66
    stylish
    -2.64
    身边的
    -2.61
    ⮑
    -2.59
    POSITIVE LOGITS
     Essentially
    2.83
     Virtually
    2.70
     Ignoring
    2.66
    These
    2.64
     Surprisingly
    2.63
    </b>
    2.56
     Throughout
    2.50
     Evidently
    2.48
     Ironically
    2.48
     Unlike
    2.45
    Activations Density 0.006%

    No Known Activations