© 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. 84913
    Prev
    Next
    INDEX
    Explanations

    web development and code file types

    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
    ImageButton
    -0.80
     traer
    -0.78
    協会
    -0.77
    enium
    -0.76
     Segu
    -0.75
    SetText
    -0.74
    rotating
    -0.72
    鎏
    -0.72
    ))}
    -0.72
    оти
    -0.71
    POSITIVE LOGITS
     generó
    0.75
     nadzieję
    0.75
    ऊ
    0.72
     Infections
    0.71
     реки
    0.71
    гии
    0.70
    igerung
    0.70
    Frage
    0.69
    Clk
    0.68
    的很
    0.66
    Activations Density 0.004%

    No Known Activations