© 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. 37351
    Prev
    Next
    INDEX
    Explanations

    logical equivalence or definitions

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

    mathematical and logical symbols

    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
     obliqu
    0.43
     dashed
    0.39
    :$
    0.37
     semej
    0.37
    算的
    0.36
    +}^{
    0.35
     diting
    0.35
    聡
    0.35
    प्ट
    0.35
     coeff
    0.35
    POSITIVE LOGITS
     prostu
    0.43
     означает
    0.43
    相当于
    0.42
     physicist
    0.42
     upravo
    0.41
     implies
    0.41
     عباره
    0.41
     implique
    0.40
     essentially
    0.40
     logically
    0.40
    Activations Density 0.001%

    No Known Activations