© 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. 94035
    Prev
    Next
    INDEX
    Explanations

    code constructs and programming keywords

    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
     iedere
    -0.90
    Externe
    -0.88
    いつも
    -0.88
    vities
    -0.87
     PROF
    -0.85
     ВЫ
    -0.85
     zapal
    -0.84
    📤
    -0.84
     jezelf
    -0.82
    衩
    -0.82
    POSITIVE LOGITS
    magitan
    0.83
     Eclipse
    0.82
     while
    0.82
     Yesterday
    0.80
    дача
    0.79
    ',['
    0.79
     сол
    0.78
     marito
    0.78
    ccccccc
    0.77
    pentine
    0.77
    Activations Density 0.002%

    No Known Activations