© 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. 59972
    Prev
    Next
    INDEX
    Explanations

    code comments and directives

    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
     hırka
    -1.11
    哈哈哈哈
    -1.05
     nace
    -0.96
     sezonu
    -0.94
     ujar
    -0.94
    ݯ
    -0.93
     román
    -0.93
    Страна
    -0.92
     dekol
    -0.92
     電動
    -0.91
    POSITIVE LOGITS
     now
    1.44
    FALL
    1.11
    Dbg
    1.07
     Now
    1.06
     insure
    1.05
    ----------------
    1.05
     tell
    1.04
     see
    0.98
     finally
    0.97
    ----------
    
    0.97
    Activations Density 0.028%

    No Known Activations