© 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. 46883
    Prev
    Next
    INDEX
    Explanations

    prepositional conjunctions

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

    and

    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
     znacz
    0.45
     zelfs
    0.45
     deflect
    0.44
     ଗ
    0.42
     deflected
    0.40
    比如说
    0.39
     gacche
    0.38
     Smartphones
    0.38
     gacchati
    0.38
     sails
    0.38
    POSITIVE LOGITS
     અને
    0.69
    および
    0.68
     आणि
    0.62
    及び
    0.59
     и
    0.55
     și
    0.54
     மற்றும்
    0.54
    rarea
    0.52
     and
    0.51
     および
    0.51
    Activations Density 0.000%

    No Known Activations