© 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. 7074
    Prev
    Next
    INDEX
    Explanations

    financial reporting terms

    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
     insured
    -0.88
    を開始
    -0.86
    ógrafo
    -0.86
    رات
    -0.82
    ficar
    -0.82
    ierung
    -0.81
     эти
    -0.80
     проис
    -0.78
     abordar
    -0.78
     этих
    -0.78
    POSITIVE LOGITS
     relating
    0.90
    meteries
    0.88
     arising
    0.85
    Including
    0.85
    ímite
    0.83
     arisen
    0.83
     lainnya
    0.83
    がありますが
    0.82
    mT
    0.82
     related
    0.81
    Activations Density 0.010%

    No Known Activations