© 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. 38125
    Prev
    Next
    INDEX
    Explanations

    apart, separated, distinct

    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
    CreateTable
    -0.82
     نیم
    -0.79
    两种
    -0.78
    почки
    -0.77
    ﾛ
    -0.76
    hasMoreElements
    -0.75
    erle
    -0.74
     フラット
    -0.74
    نیم
    -0.74
     programas
    -0.72
    POSITIVE LOGITS
     apart
    6.13
    apart
    4.47
    Apart
    3.92
     Apart
    3.77
     APART
    2.69
     appart
    2.38
     auseinander
    2.36
     aside
    2.22
     aparte
    2.20
     separated
    1.77
    Activations Density 0.047%

    No Known Activations