© 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. 80502
    Prev
    Next
    INDEX
    Explanations

    specific entities or roles

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

    centuries

    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
    底下
    0.44
    ig
    0.42
    ృ
    0.40
    n
    0.38
    ЛА
    0.38
    zt
    0.38
    vr
    0.38
    Shi
    0.38
    DRI
    0.38
    2
    0.38
    POSITIVE LOGITS
     inquis
    0.54
     sultan
    0.52
    Ꞌ
    0.50
     سلطان
    0.49
     shinobi
    0.48
     nirv
    0.47
     testator
    0.46
     Yeshu
    0.46
     dreadful
    0.46
    ulfate
    0.46
    Activations Density 0.000%

    No Known Activations