© 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. 93881
    Prev
    Next
    INDEX
    Explanations

    node, pointer, struct, class, ATA, Introduction, Wednesday

    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
     civilización
    -0.81
     kontroli
    -0.81
     poderia
    -0.80
    successor
    -0.78
     ürün
    -0.77
    Happy
    -0.76
    winter
    -0.76
    🇿
    -0.75
    ettet
    -0.75
    🏉
    -0.74
    POSITIVE LOGITS
     created
    0.84
    委員
    0.82
     create
    0.80
    ІІ
    0.79
     According
    0.78
     according
    0.78
     creates
    0.77
    ophone
    0.73
     בלב
    0.72
    estación
    0.72
    Activations Density 0.006%

    No Known Activations