© 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. 22-GEMMASCOPE-RES-131K
    7. 70572
    Prev
    Next
    INDEX
    Explanations

    for loop variable in list

    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_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
    yyj
    -1.15
     anderen
    -1.09
    อื่น
    -0.98
     a
    -0.98
    鲜血
    -0.94
     configuração
    -0.94
     aquarela
    -0.93
    田市
    -0.92
     classificação
    -0.92
     korrekt
    -0.92
    POSITIVE LOGITS
     it
    1.15
    每個
    1.03
    Each
    1.00
    它們
    0.98
     stair
    0.98
    这样做
    0.95
     might
    0.91
    قديم
    0.89
    منى
    0.88
    dal
    0.88
    Activations Density 0.002%

    No Known Activations