© 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. 52760
    Prev
    Next
    INDEX
    Explanations

    numbers and names

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

    tasks, exposure, humans, grasslands

    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
     روایت
    0.49
    ėj
    0.48
     प्रिज्म
    0.48
    prache
    0.47
    べき
    0.44
    ކ
    0.44
    ോദ
    0.43
    étique
    0.43
     प्यारी
    0.43
    וג
    0.42
    POSITIVE LOGITS
    i
    0.46
     alternativas
    0.46
    愈
    0.45
     integrantes
    0.44
     telefono
    0.44
     dyr
    0.43
     telefone
    0.43
     fiberglass
    0.42
    路的
    0.42
    <unused1030>
    0.42
    Activations Density 0.000%

    No Known Activations