© 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. 119063
    Prev
    Next
    INDEX
    Explanations

    loan approval

    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
     tratamientos
    -0.89
    iferous
    -0.85
     saúde
    -0.83
    hardy
    -0.82
     всички
    -0.82
     Introducción
    -0.81
     políticos
    -0.80
     mua
    -0.79
     frenos
    -0.79
    candy
    -0.77
    POSITIVE LOGITS
     bad
    1.65
    Bad
    1.58
     your
    1.34
     Bad
    1.30
    bad
    1.29
     payday
    1.20
    BAD
    1.13
    Approval
    1.12
     you
    1.10
     approval
    1.07
    Activations Density 0.012%

    No Known Activations