© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103404
    Prev
    Next
    INDEX
    Explanations

    Objective-C code snippets

    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
    xture
    -0.84
    urit
    -0.80
    texttt
    -0.79
    reter
    -0.79
    htar
    -0.78
    reros
    -0.77
    icei
    -0.74
    搡
    -0.74
     underway
    -0.73
    打的
    -0.71
    POSITIVE LOGITS
     Preto
    0.88
    ʾ
    0.77
    $\$
    0.77
    Jahre
    0.76
    recyclerView
    0.75
    Coppa
    0.75
    IPMENT
    0.74
     obje
    0.74
    ୌ
    0.73
     MEC
    0.71
    Activations Density 0.177%

    No Known Activations