© 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. 5671
    Prev
    Next
    INDEX
    Explanations

    falsification, til wednesday

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

    information entries definition

    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
    qk
    0.51
     infin
    0.49
     superconducting
    0.46
     infinito
    0.46
    کنند
    0.44
    씀
    0.43
     infinit
    0.43
     ニュー
    0.43
     hib
    0.43
     ঢাকায়
    0.42
    POSITIVE LOGITS
    ruar
    0.49
    För
    0.48
    шинство
    0.47
    ેર
    0.47
    璈
    0.46
     be
    0.45
    ータル
    0.45
     состав
    0.44
     डेब्यू
    0.44
     има
    0.44
    Activations Density 0.000%

    No Known Activations