© 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. 86146
    Prev
    Next
    INDEX
    Explanations

    specific technical or financial terms

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

    list items

    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
    benar
    0.55
    娼
    0.52
    kq
    0.49
    AllRef
    0.49
     биографи
    0.48
     चला
    0.47
    വില്‍
    0.47
     किरदार
    0.47
     मतदार
    0.47
    aaa
    0.47
    POSITIVE LOGITS
    ப
    0.46
    汉
    0.46
     árbol
    0.45
    ق
    0.44
     Destruction
    0.43
     alemán
    0.43
     Mathematik
    0.43
    自动
    0.43
    PYTHON
    0.41
     Dtsch
    0.41
    Activations Density 0.001%

    No Known Activations