© 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. 10-GEMMASCOPE-RES-131K
    7. 130742
    Prev
    Next
    INDEX
    Explanations

    F1 rats and mice

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

    the letter 'F' followed by the number '1', typically appearing in technical contexts like product codes, file formats, or formula references.

    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_10/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
    
    -2.23
    鋮
    -2.06
     двумя
    -2.05
    на
    -1.99
     excruciating
    -1.96
    เกง
    -1.95
     efficiently
    -1.92
    罣
    -1.91
     convincingly
    -1.91
    塤
    -1.91
    POSITIVE LOGITS
    (
    2.20
    </h3>
    1.99
     illustratie
    1.98
    ts
    1.98
     tuan
    1.91
    腠
    1.91
    鲽
    1.89
    你的
    1.88
     présentés
    1.85
    闼
    1.84
    Activations Density 0.010%

    No Known Activations