© 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. 110999
    Prev
    Next
    INDEX
    Explanations

    pointer dereferencing in code

    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
     процес
    -0.87
    *
    -0.83
    ный
    -0.83
    はじ
    -0.82
     all
    -0.78
    rý
    -0.78
    ihnachten
    -0.76
     Alloy
    -0.76
    OVID
    -0.74
    ってない
    -0.74
    POSITIVE LOGITS
    reinterpret
    1.19
     їх
    1.14
     jejich
    1.09
    their
    1.08
     тях
    1.07
     mereka
    1.05
     tím
    1.04
     ingenieros
    1.03
     bê
    1.03
     их
    1.03
    Activations Density 0.002%

    No Known Activations