© 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. 60369
    Prev
    Next
    INDEX
    Explanations

    computer science contexts

    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
    tslib
    -0.73
     statistical
    -0.72
     regime
    -0.71
     returned
    -0.69
    첼
    -0.68
    CDF
    -0.67
    conform
    -0.67
    빈
    -0.65
     Nietzsche
    -0.65
    caden
    -0.65
    POSITIVE LOGITS
     Turing
    0.94
     Computer
    0.91
    Languages
    0.90
    Computer
    0.83
    ALG
    0.82
    ⍝
    0.81
     Weizen
    0.81
    ACM
    0.79
    љ
    0.79
     Languages
    0.79
    Activations Density 0.050%

    No Known Activations