© 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. 66961
    Prev
    Next
    INDEX
    Explanations

    vice versa

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

    vice and conversely

    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
    uencia
    0.42
    bmc
    0.38
    牝
    0.37
     END
    0.35
    erosion
    0.35
     competir
    0.35
    郆
    0.35
     dj
    0.35
    prox
    0.34
     LAYER
    0.34
    POSITIVE LOGITS
     vice
    1.22
     reciproc
    1.09
     reciprocal
    1.01
     conversely
    0.99
    逆に
    0.95
    Conversely
    0.93
     recipro
    0.92
    vice
    0.92
     Conversely
    0.91
     наоборот
    0.89
    Activations Density 0.195%

    No Known Activations