© 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. 60098
    Prev
    Next
    INDEX
    Explanations

    integer variable declarations

    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
     induk
    -0.95
     sesi
    -0.88
     kosme
    -0.88
     aktivi
    -0.87
     kirim
    -0.86
    <0xA3>
    -0.84
     lauk
    -0.84
     laku
    -0.83
     kapsul
    -0.83
    ξύ
    -0.82
    POSITIVE LOGITS
     temporary
    1.40
    flag
    1.23
     copy
    1.23
     flag
    1.20
     result
    1.18
     count
    1.17
     I
    1.13
    temp
    1.11
     temp
    1.11
     i
    1.09
    Activations Density 0.028%

    No Known Activations