© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18992
    Prev
    Next
    INDEX
    Explanations

    instance key

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

    page, daughter, commodity, touch, Landscape

    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_31_width_262k_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
    так
    0.51
    ness
    0.47
    ва
    0.45
    もし
    0.45
    後
    0.43
    чи
    0.42
    일상
    0.42
    elson
    0.42
    зна
    0.41
    後ろ
    0.41
    POSITIVE LOGITS
     vardı
    0.66
     enzim
    0.52
     udziel
    0.50
     felicidade
    0.49
     francês
    0.48
     ferrovi
    0.46
    MBean
    0.46
     ekspl
    0.46
     vampires
    0.46
     ແ
    0.45
    Activations Density 0.000%

    No Known Activations