Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110371
    Prev
    Next
    INDEX
    Explanations

    copyright and license notices

    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
    rąg
    -0.77
    альное
    -0.76
    今日も
    -0.76
     intentando
    -0.75
     niekoľ
    -0.75
     vrije
    -0.75
    今天的
    -0.73
     IDA
    -0.73
    drawiam
    -0.72
    למה
    -0.71
    POSITIVE LOGITS
    Market
    0.91
    League
    0.86
     Programming
    0.84
    study
    0.81
     MARKET
    0.81
    Programmer
    0.80
    tika
    0.79
     Programmer
    0.79
    JFrame
    0.78
     jasa
    0.78
    Activations Density 0.024%

    No Known Activations