© 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. 70376
    Prev
    Next
    INDEX
    Explanations

    pas words

    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_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
    髕
    -3.67
    神
    -3.45
    肏
    -3.34
     イラストレーション
    -3.13
    茕
    -3.13
    鄖
    -3.08
    踽
    -3.03
     abbildung
    -3.00
    柺
    -3.00
    技术的
    -2.97
    POSITIVE LOGITS
    5
    3.23
    e
    3.14
    ”
    3.09
    According
    2.88
    Unlike
    2.80
    8
    2.78
    Interestingly
    2.77
     Responding
    2.73
    When
    2.69
    6
    2.63
    Activations Density 0.004%

    No Known Activations