© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11084
    Prev
    Next
    INDEX
    Explanations

    numbers and quotes

    np_acts-logits-general · gemini-2.5-flash-lite

    disclaimer about sensitive themes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyoruz
    0.47
    umuza
    0.46
    我们也
    0.44
    <h3>
    0.43
     esperamos
    0.43
     Journalist
    0.43
    yoruz
    0.42
     entrevista
    0.42
    ersi
    0.42
    umni
    0.41
    POSITIVE LOGITS
     δὲ
    0.47
     related
    0.46
     hymns
    0.46
     hymn
    0.46
    頓
    0.44
    োহণ
    0.43
     footnote
    0.42
     ganglions
    0.42
     memorials
    0.42
     ঈশ্বর
    0.41
    Activations Density 0.142%

    No Known Activations