Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8112
    Prev
    Next
    INDEX
    Explanations

    modified Delphi method, expert techniques

    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
     ſol
    -0.98
    甶
    -0.93
     aviones
    -0.91
     trám
    -0.87
     quatrième
    -0.87
     kategorii
    -0.86
     correos
    -0.85
    lillah
    -0.85
     dát
    -0.84
     descuentos
    -0.84
    POSITIVE LOGITS
     Delphi
    1.38
     expert
    1.27
     SWOT
    1.22
     using
    1.20
     use
    1.12
     techniques
    1.09
     methods
    1.06
     cost
    1.02
     Monte
    1.02
     simple
    1.02
    Activations Density 0.062%

    No Known Activations