© 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. 69248
    Prev
    Next
    INDEX
    Explanations

    typescript file extensions

    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
    .
    -3.23
    鸯
    -2.41
    来自于
    -2.34
    ～。
    -2.34
    撘
    -2.23
    0
    -2.19
     CHECKBOX
    -2.14
     itſelf
    -2.09
    CHREIB
    -2.08
    薆
    -2.06
    POSITIVE LOGITS
    )
    3.05
    !"
    2.61
    蕷
    2.59
    樒
    2.48
    TS
    2.42
    .”
    2.38
    er
    2.38
     You
    2.33
     figuring
    2.23
    ৢ
    2.22
    Activations Density 0.010%

    No Known Activations