© 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. 22-GEMMASCOPE-RES-131K
    7. 72018
    Prev
    Next
    INDEX
    Explanations

    questions, scientific terms

    np_acts-logits-general · gemini-2.5-flash-lite

    geographic locations and place names, particularly Spanish locations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     both
    -1.10
     after
    -1.09
     perhaps
    -1.08
     several
    -1.04
     znaleźć
    -0.91
     very
    -0.91
     this
    -0.90
    ｨ
    -0.89
     tubos
    -0.89
     three
    -0.89
    POSITIVE LOGITS
     vetores
    1.13
    撅
    1.03
     alho
    1.03
     استفاده
    0.98
     oliveira
    0.94
    Gost
    0.93
     omfatt
    0.92
     aynı
    0.91
    maximize
    0.90
     municipale
    0.90
    Activations Density 0.000%

    No Known Activations