© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8788
    Prev
    Next
    INDEX
    Explanations

    cash back, advances, instruments, or account

    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
     einzigartige
    -2.09
    ’
    -2.03
     spezielle
    -1.95
     klassische
    -1.91
     weiße
    -1.88
    の人気
    -1.88
     charming
    -1.83
     großartige
    -1.82
     terrific
    -1.77
     soooo
    -1.77
    POSITIVE LOGITS
    Through
    1.93
     There
    1.91
    Sometimes
    1.84
    there
    1.84
    Unlike
    1.82
    Usually
    1.76
    Despite
    1.74
    Having
    1.73
    Often
    1.73
    ٸ
    1.70
    Activations Density 0.017%

    No Known Activations