© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2818
    Prev
    Next
    INDEX
    Explanations

    generated code or specific word beginnings

    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
    Ḥ
    -0.82
     ChromeDriver
    -0.81
    offsetTop
    -0.80
     their
    -0.78
     brasil
    -0.77
    ạng
    -0.77
    ('--
    -0.77
    ır
    -0.76
    갖
    -0.76
    setFont
    -0.75
    POSITIVE LOGITS
     ده
    0.90
     butts
    0.89
     라이
    0.87
    Apt
    0.86
    Gloss
    0.85
     نوزاد
    0.81
     nõ
    0.81
    Mojo
    0.81
     岛
    0.80
    Shallow
    0.79
    Activations Density 0.014%

    No Known Activations