© 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. 34-GEMMASCOPE-RES-131K
    7. 2090
    Prev
    Next
    INDEX
    Explanations

    credit reporting and financial status

    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
    équipements
    -0.87
    mAuth
    -0.85
     bedien
    -0.84
    plit
    -0.81
    вающая
    -0.78
     مشروع
    -0.78
    saw
    -0.77
     anunció
    -0.75
    GOT
    -0.74
     CHANGES
    -0.73
    POSITIVE LOGITS
     reporting
    1.30
     negatively
    1.15
     reported
    1.13
     negative
    1.11
     history
    1.10
     accounts
    1.05
     report
    1.02
     Reporting
    1.02
    reporting
    0.98
     positive
    0.96
    Activations Density 0.012%

    No Known Activations