© 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. 231189
    Prev
    Next
    INDEX
    Explanations

    criticizing China

    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
    å
    0.47
     существенно
    0.45
     Goldberg
    0.45
     KT
    0.44
     Goff
    0.43
    打破
    0.42
     betyd
    0.41
    ۥ
    0.41
     gestation
    0.40
    {
    0.40
    POSITIVE LOGITS
    сите
    0.54
    נ
    0.51
     métall
    0.50
    Browser
    0.49
    ાઓ
    0.48
    phenylsulfanyl
    0.47
     Ом
    0.47
    мос
    0.46
    ем
    0.46
     し
    0.46
    Activations Density 0.000%

    No Known Activations